© 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. 204287
    Prev
    Next
    INDEX
    Explanations

    orderly transitions

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

    moderate alcohol, symbolic rules

    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
    Initializing
    0.47
    ईन
    0.47
    Ĝ
    0.47
    Enumerable
    0.44
     wünschen
    0.44
    AIN
    0.43
    Gravity
    0.42
     Gathering
    0.42
    Four
    0.42
     ĝi
    0.42
    POSITIVE LOGITS
    ޟ
    0.47
    ாம
    0.43
     Nelly
    0.41
    ुलिस
    0.41
     reiter
    0.41
     Horm
    0.41
    ιστή
    0.40
     bans
    0.40
     policía
    0.39
     weakened
    0.39
    Activations Density 0.002%

    No Known Activations