© 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. 113231
    Prev
    Next
    INDEX
    Explanations

    moving video

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

    refused to sell

    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
    lando
    0.50
    R
    0.49
    tras
    0.49
    Lands
    0.47
    time
    0.47
    :],
    0.47
    lang
    0.46
    Forward
    0.46
    Find
    0.45
    l
    0.45
    POSITIVE LOGITS
    鈮
    0.58
     denominador
    0.53
     handleSubmit
    0.53
    紙
    0.52
    焲
    0.52
     sujeito
    0.52
    粓
    0.51
    筅
    0.51
    價值
    0.50
     modalCard
    0.50
    Activations Density 0.001%

    No Known Activations