© 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. 51974
    Prev
    Next
    INDEX
    Explanations

    loved it

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

    Embedding, Encoding, voice, localstorage

    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
    HJ
    0.45
     HJ
    0.45
     ব্যাবস্থা
    0.42
     অ্য
    0.42
     '.';
    0.41
    Gallery
    0.40
     گرم
    0.40
    Hemat
    0.39
     Chiến
    0.39
    VING
    0.39
    POSITIVE LOGITS
    ils
    0.47
    eur
    0.43
    urses
    0.43
    ants
    0.42
     proie
    0.42
     onboarding
    0.41
    atore
    0.41
    }%
    0.41
    ț
    0.40
    lings
    0.39
    Activations Density 0.008%

    No Known Activations