© 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. 31946
    Prev
    Next
    INDEX
    Explanations

    pins or cream

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

    lashes and physical traits

    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
     वास्तु
    0.55
     твер
    0.47
    ре
    0.46
    हार्
    0.46
    гор
    0.46
    й
    0.45
    си
    0.45
    𝐬
    0.45
    懺
    0.44
    מא
    0.44
    POSITIVE LOGITS
     employability
    0.45
     nghề
    0.42
     headset
    0.42
    GISL
    0.41
     adulto
    0.41
     lineman
    0.40
     Leben
    0.40
     adult
    0.39
     Drosophila
    0.39
     slalom
    0.39
    Activations Density 0.000%

    No Known Activations