© 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. 20603
    Prev
    Next
    INDEX
    Explanations

    someone you

    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
     nuevos
    0.40
     connotations
    0.40
     mediante
    0.38
    ｭ
    0.38
     éxitos
    0.37
     כל
    0.37
    \-
    0.36
    ርስ
    0.36
     casos
    0.36
    unce
    0.36
    POSITIVE LOGITS
     शायद
    0.48
     হয়ত
    0.44
    或许
    0.43
     getActivity
    0.42
     হয়ত
    0.41
     আসলে
    0.40
     എന്നത്
    0.40
     Έ
    0.39
     someone
    0.39
    тивный
    0.39
    Activations Density 0.017%

    No Known Activations