© 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. 32147
    Prev
    Next
    INDEX
    Explanations

    URLs containing 'rural'

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

    structure and code organization

    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
    ͡
    0.39
     åt
    0.38
     సాధ
    0.38
     sociological
    0.37
     র
    0.37
    ńcz
    0.37
    вяз
    0.36
     HashSet
    0.36
     重量
    0.36
    ją
    0.36
    POSITIVE LOGITS
    損傷
    0.41
    credential
    0.39
    AMI
    0.39
     লোকদের
    0.39
    BACK
    0.38
    ⅾ
    0.38
    <h1>
    0.38
    backs
    0.38
    pta
    0.38
    tags
    0.38
    Activations Density 0.004%

    No Known Activations