© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14099
    Prev
    Next
    INDEX
    Explanations

    still ongoing

    np_acts-logits-general · gemini-2.5-flash-lite

    still, continuing state

    np_acts-logits-general · gemini-2.5-flash-lite

    still

    np_max-act · claude-4-5-sonnetTriggered by @sk5695

    still

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     already
    0.63
     bereits
    0.53
    े
    0.52
     kolei
    0.52
     уже
    0.51
     Already
    0.50
    emen
    0.50
     deven
    0.50
     coincided
    0.50
     вже
    0.50
    POSITIVE LOGITS
     fortfarande
    0.99
    仍
    0.96
    仍然
    0.93
     هنوز
    0.92
     vẫn
    0.91
    still
    0.88
    Still
    0.86
     Still
    0.85
     STILL
    0.84
     still
    0.83
    Activations Density 0.233%

    No Known Activations