© 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. 27151
    Prev
    Next
    INDEX
    Explanations

    directly, straight, directly

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

    direct requirements

    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
    .
    0.46
     será
    0.40
    ječ
    0.40
    and
    0.40
    also
    0.40
    也不能
    0.39
     recast
    0.39
    andid
    0.39
    never
    0.39
     և
    0.39
    POSITIVE LOGITS
     सीधा
    0.57
     সরাসরি
    0.53
     напрямую
    0.51
    बाग
    0.50
     직접
    0.49
     सीधे
    0.49
    侷
    0.48
     फटाफट
    0.48
     грамо
    0.48
     ',',
    0.47
    Activations Density 0.000%

    No Known Activations