© 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. 23337
    Prev
    Next
    INDEX
    Explanations

    details about or for

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

    detail or details

    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
     exercices
    0.44
    кових
    0.43
    批判
    0.41
     transdu
    0.40
     validations
    0.40
    }\|
    0.39
    度の
    0.39
    整個
    0.39
     diastolic
    0.39
     vetting
    0.38
    POSITIVE LOGITS
     Det
    0.50
     Detail
    0.46
    Detail
    0.45
    sidebar
    0.44
    Det
    0.44
     Details
    0.43
    details
    0.43
    DETAIL
    0.42
     Detalles
    0.42
     detalle
    0.42
    Activations Density 0.008%

    No Known Activations