© 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. 160012
    Prev
    Next
    INDEX
    Explanations

    room service, butter, track, fall

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

    short answer explanations or opinions

    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
     MQTT
    0.49
    ኋ
    0.48
     शेवट
    0.46
    मोदी
    0.46
    मनी
    0.45
     シュ
    0.45
     स्टा
    0.43
    鈴木
    0.43
     pokemon
    0.42
    ್
    0.42
    POSITIVE LOGITS
    یی
    0.47
    ieron
    0.45
     بیس
    0.45
    ifle
    0.44
    hier
    0.44
    ünden
    0.43
    ieuse
    0.43
    digo
    0.42
    ibid
    0.42
    eden
    0.41
    Activations Density 0.001%

    No Known Activations