© 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. 237934
    Prev
    Next
    INDEX
    Explanations

    ultrasonic ( motors and company the

    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
    ṓ
    0.51
    defer
    0.46
     많이
    0.45
    legg
    0.45
     alguno
    0.45
    gar
    0.45
     Lest
    0.44
    asta
    0.44
     யான
    0.44
    osing
    0.44
    POSITIVE LOGITS
     infiltrated
    0.48
    APPROVED
    0.46
    <0x80>
    0.45
     serangan
    0.41
     launched
    0.41
    Ε
    0.41
    ಿನಿ
    0.40
     aws
    0.40
     seabed
    0.40
     particle
    0.40
    Activations Density 0.001%

    No Known Activations