© 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. 65928
    Prev
    Next
    INDEX
    Explanations

    languages including common

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

    authenticator codes and sms

    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
    ve
    0.43
    vaient
    0.40
    ()]
    0.38
    ®.
    0.38
    ]
    0.38
    움
    0.38
    <0x8A>
    0.38
     divisions
    0.38
    stances
    0.36
     preparations
    0.36
    POSITIVE LOGITS
     結婚
    0.54
     カラ
    0.54
     מ
    0.52
     kaos
    0.52
     ทํา
    0.52
     れ
    0.51
     ラ
    0.50
     فريبي
    0.50
     家庭
    0.50
     și
    0.50
    Activations Density 0.000%

    No Known Activations