© 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. 40-GEMMASCOPE-2-RES-65K
    7. 52796
    Prev
    Next
    INDEX
    Explanations

    harmless activity, original wording, horribly misguided

    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_40_width_65k_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
     provoquer
    0.40
     المج
    0.40
     iri
    0.40
     podendo
    0.39
     може
    0.38
     môžu
    0.38
    먹
    0.37
     đứa
    0.37
     వచ్చ
    0.37
     thể
    0.37
    POSITIVE LOGITS
    ishment
    0.43
    /');
    0.40
     हाई
    0.39
     HYDRO
    0.38
    ১৭
    0.38
    火箭
    0.38
    --’
    0.38
    chant
    0.38
    امین
    0.38
    tach
    0.37
    Activations Density 0.000%

    No Known Activations