© 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. 202345
    Prev
    Next
    INDEX
    Explanations

    emerges from, different filters, finest method

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

    examples with `like`

    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
    <unused55>
    0.48
     తెలిప
    0.48
    icu
    0.47
     બાળકો
    0.47
     প্রার্থীদের
    0.46
     लैंग
    0.46
    ällen
    0.45
     penilaian
    0.45
    нов
    0.45
    εσ
    0.44
    POSITIVE LOGITS
    '
    0.51
    "
    0.47
    可以说
    0.46
    État
    0.45
    viso
    0.42
    Operation
    0.42
    ”
    0.41
     États
    0.41
    て
    0.41
    त
    0.40
    Activations Density 0.001%

    No Known Activations