© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224761
    Prev
    Next
    INDEX
    Explanations

    business as usual

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

    foreign languages and harmful content

    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
     traité
    0.45
     estil
    0.44
     údaje
    0.44
    а
    0.44
     ab
    0.43
     equate
    0.43
    تين
    0.43
     était
    0.42
     seed
    0.42
    стрі
    0.41
    POSITIVE LOGITS
     मजबूर
    0.50
     떠
    0.49
    satunya
    0.48
    袍
    0.45
    物联网
    0.45
    দম
    0.44
     நிறுத்த
    0.43
    㷅
    0.43
    ementara
    0.42
     সিংহ
    0.42
    Activations Density 0.000%

    No Known Activations