© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209054
    Prev
    Next
    INDEX
    Explanations

    home equipment

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

    half hour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    出て
    0.49
     pede
    0.48
    ид
    0.48
     phosphory
    0.47
     fratello
    0.47
     quale
    0.46
     contatto
    0.46
    ｎ
    0.46
    represent
    0.45
    turno
    0.45
    POSITIVE LOGITS
     Strengthen
    0.51
     Podcasts
    0.49
     Apps
    0.48
     Inflation
    0.46
     infographics
    0.46
     Helpline
    0.46
     Helping
    0.46
     ఇవ్వ
    0.46
     stressors
    0.45
     интернете
    0.45
    Activations Density 0.001%

    No Known Activations