© 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. 55137
    Prev
    Next
    INDEX
    Explanations

    with numbers or lists

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

    north, east, west directions

    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
    IZ
    0.44
     Reduces
    0.41
    ZY
    0.39
     reducing
    0.39
    khar
    0.39
    一边
    0.39
    g
    0.39
     God
    0.38
    เหน
    0.38
     reduc
    0.38
    POSITIVE LOGITS
    মধ
    0.51
     الحياة
    0.51
    Ẩ
    0.49
    Ố
    0.47
     પ્રતિબ
    0.47
     दैट
    0.47
     цве
    0.47
     سف
    0.46
     ਵੱ
    0.46
     év
    0.46
    Activations Density 0.000%

    No Known Activations