© 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. 24888
    Prev
    Next
    INDEX
    Explanations

    has to, would have

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

    numbering from the right

    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
    la
    0.44
    pn
    0.42
     Baltes
    0.42
     I
    0.42
    </b>
    0.42
    borderColor
    0.42
    вают
    0.41
     n
    0.40
     obsession
    0.39
     poolside
    0.39
    POSITIVE LOGITS
     yil
    0.51
    ゴミ
    0.49
    ೆಂಟ್
    0.49
    ныгы
    0.47
    영화
    0.45
    ంగ్
    0.45
     gått
    0.44
     хоче
    0.44
     metų
    0.43
    브
    0.43
    Activations Density 0.000%

    No Known Activations