© 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. 156869
    Prev
    Next
    INDEX
    Explanations

    negativity and threats

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

    context history empathy need rudimentary

    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
     that
    0.51
     iphdr
    0.45
    iture
    0.45
    t
    0.45
    𝒊
    0.44
     Climate
    0.43
    ulating
    0.42
     .
    0.42
     interrupt
    0.41
     for
    0.41
    POSITIVE LOGITS
     disgruntled
    0.64
     protégé
    0.58
     победи
    0.58
     большой
    0.56
     بزرگ
    0.55
     אחד
    0.55
     одной
    0.54
     दो
    0.52
    besar
    0.52
     devout
    0.52
    Activations Density 0.000%

    No Known Activations