© 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. 176145
    Prev
    Next
    INDEX
    Explanations

    phrases with "no point" or "choosing from"

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

    rates, fees, and resolutions

    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
    笈
    0.47
    ಾನೂ
    0.47
     bestät
    0.43
     writer
    0.42
    ᕆ
    0.42
     revisiting
    0.41
    进攻
    0.41
     familie
    0.40
     AGO
    0.40
    ීම
    0.39
    POSITIVE LOGITS
    Arr
    0.53
    onymous
    0.48
    C
    0.47
    anyag
    0.45
    Fax
    0.44
    oy
    0.43
     場所
    0.43
    Place
    0.43
    ’
    0.43
     전국
    0.42
    Activations Density 0.000%

    No Known Activations