© 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. 39341
    Prev
    Next
    INDEX
    Explanations

    quoted or enumerated items

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

    closing brackets and commas

    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
     courants
    0.44
     Elektrokhimiya
    0.43
     heps
    0.40
    =\"
    0.39
    РЕ
    0.39
    ضور
    0.39
    کنش
    0.39
    =\""
    0.39
     algoritmo
    0.38
     mischiev
    0.38
    POSITIVE LOGITS
    ions
    0.44
    second
    0.42
    cabin
    0.41
    ies
    0.41
    ited
    0.41
    Another
    0.41
    ବା
    0.40
    鹿児
    0.40
    ikt
    0.40
    osil
    0.40
    Activations Density 0.000%

    No Known Activations