© 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. 162468
    Prev
    Next
    INDEX
    Explanations

    describing clothing conditions

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

    discuss enrolling

    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
    вач
    0.49
    depos
    0.47
    К
    0.47
    вача
    0.46
    รอ
    0.44
    Deposito
    0.44
    ParamNum
    0.42
    נה
    0.41
     mansions
    0.41
     deposits
    0.41
    POSITIVE LOGITS
     THAT
    0.51
     oor
    0.51
     passaram
    0.50
     utf
    0.48
    の原因
    0.46
     病
    0.45
     daniel
    0.45
     fanden
    0.45
    ликт
    0.45
    ated
    0.44
    Activations Density 0.000%

    No Known Activations