© 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-65K
    7. 51230
    Prev
    Next
    INDEX
    Explanations

    Requires the

    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_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
     하다
    0.50
     технику
    0.46
    😪
    0.43
     기타
    0.43
    ,\,\
    0.42
    ]]);
    0.41
    getragen
    0.41
    Repr
    0.41
    atau
    0.41
     наро
    0.41
    POSITIVE LOGITS
     to
    0.49
     een
    0.47
     două
    0.45
     a
    0.44
     A
    0.42
     f
    0.42
     earnings
    0.41
     twee
    0.41
     doua
    0.39
    arbeitung
    0.39
    Activations Density 0.009%

    No Known Activations