© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81759
    Prev
    Next
    INDEX
    Explanations

    get away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    0.46
    L
    0.46
     personal
    0.46
     hostile
    0.46
     creative
    0.45
    s
    0.42
    NO
    0.42
    싫
    0.41
     über
    0.40
     Circuit
    0.40
    POSITIVE LOGITS
    𒌅
    0.51
     صحی
    0.51
     QnrB
    0.49
     tetapi
    0.49
     යු
    0.48
    टाइ
    0.48
     astrophysics
    0.47
    کت
    0.47
    लेकिन
    0.46
    inträ
    0.46
    Activations Density 0.002%

    No Known Activations