© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42692
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by new sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    F
    0.51
    format
    0.46
    deterministic
    0.45
    formance
    0.44
    hybrid
    0.43
    Electron
    0.43
    ported
    0.43
     የም
    0.43
     जहरी
    0.43
     hybrid
    0.42
    POSITIVE LOGITS
     décadas
    0.49
     anci
    0.46
     sentir
    0.46
    <0xD8>
    0.45
     moradores
    0.45
     heeft
    0.44
     artículos
    0.44
     অনুভূত
    0.43
     cricketers
    0.43
     industria
    0.42
    Activations Density 0.005%

    No Known Activations