© 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. 220150
    Prev
    Next
    INDEX
    Explanations

    other languages and situations

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

    listing and established connections

    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
     with
    0.61
    '
    0.48
     bright
    0.48
    bright
    0.47
    하실
    0.44
     virtual
    0.42
     titled
    0.42
     LIF
    0.42
     $
    0.40
    ản
    0.40
    POSITIVE LOGITS
     Faktoren
    0.54
     入っ
    0.54
     spaceleft
    0.54
     আয়নগুলি
    0.53
     flancs
    0.51
    स्ताना
    0.49
     Архив
    0.49
     परिस्थितीत
    0.49
     орби
    0.48
     ฝ
    0.48
    Activations Density 0.000%

    No Known Activations