© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 66931
    Prev
    Next
    INDEX
    Explanations

    performance metrics

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

    service, troubleshooting, version, probability

    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
    LE
    0.46
    CON
    0.45
     ఇటీ
    0.45
    debounce
    0.45
    ले
    0.44
     resonates
    0.43
    레
    0.43
    ペ
    0.42
    Ọ
    0.42
     doesnt
    0.41
    POSITIVE LOGITS
     Veterinary
    0.48
     Virology
    0.48
     Biochemistry
    0.45
     시설
    0.45
     Biotechnology
    0.44
     Thurs
    0.42
    বৃহস্পতিবার
    0.42
     Tyl
    0.41
     Cina
    0.40
    ంధ్ర
    0.40
    Activations Density 0.000%

    No Known Activations