© 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. 40360
    Prev
    Next
    INDEX
    Explanations

    verbs following "to" or "para"

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

    danger, manipulation, critical systems

    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
    ar
    0.55
    as
    0.54
    an
    0.48
     kindness
    0.47
    u
    0.46
    чень
    0.45
     அனைத்தும்
    0.44
    ة
    0.44
    a
    0.44
    i
    0.44
    POSITIVE LOGITS
    textColour
    0.47
    ডিয়াম
    0.47
     ওষুধ
    0.46
     寝
    0.46
     SimSun
    0.43
     addr
    0.42
     প্রচ
    0.42
    QTTR
    0.42
     antiserum
    0.42
     राजग
    0.42
    Activations Density 0.000%

    No Known Activations