© 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. 248285
    Prev
    Next
    INDEX
    Explanations

    selling property or access

    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
     primes
    0.50
    奮
    0.46
    ators
    0.43
     halen
    0.43
     descending
    0.42
     बोलने
    0.42
    アカ
    0.42
     മു
    0.42
     folders
    0.42
     ak
    0.40
    POSITIVE LOGITS
    ceğim
    0.51
    ä
    0.51
    я
    0.50
    ług
    0.48
    ینک
    0.48
     newfound
    0.46
    летка
    0.46
    лур
    0.46
    ifferenti
    0.45
    벚
    0.44
    Activations Density 0.002%

    No Known Activations