© 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. 131104
    Prev
    Next
    INDEX
    Explanations

    an adjective noun

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

    predicting the next word

    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
    oir
    0.51
    ræ
    0.51
    nia
    0.50
    <0x80>
    0.50
    opp
    0.49
    rod
    0.49
    od
    0.48
    rę
    0.48
    hire
    0.46
    oz
    0.46
    POSITIVE LOGITS
    掴
    0.53
    סט
    0.50
     asta
    0.49
     apellido
    0.49
     pyaar
    0.47
    נטי
    0.46
     adhik
    0.46
    LEMN
    0.45
    adaş
    0.44
     apat
    0.43
    Activations Density 0.000%

    No Known Activations