© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38108
    Prev
    Next
    INDEX
    Explanations

    places and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    א
    0.50
     वगैरह
    0.45
    ณิต
    0.43
    öse
    0.43
     détermine
    0.43
    ruvic
    0.42
     mathematic
    0.42
     posteriores
    0.42
    性和
    0.41
    Ǥ
    0.41
    POSITIVE LOGITS
     tourism
    0.47
     showrooms
    0.46
     शानदार
    0.46
     picnics
    0.45
    、（
    0.40
    光
    0.40
    মনের
    0.40
    銀座
    0.39
    opens
    0.39
     picnic
    0.38
    Activations Density 0.004%

    No Known Activations