© 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. 203704
    Prev
    Next
    INDEX
    Explanations

    any followed by consign, reason, or loss

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

    not bad, optional, vs. began

    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
     אך
    0.47
     temiz
    0.43
    ._
    0.42
    ].
    0.42
    iarism
    0.41
     ইউনিভার
    0.41
     Frü
    0.41
     geometry
    0.41
     Geometry
    0.41
     Де
    0.40
    POSITIVE LOGITS
    See
    0.48
     riddled
    0.44
    ferred
    0.42
    ണ
    0.42
    ྛ
    0.42
    तो
    0.42
    ョ
    0.41
    specs
    0.41
     noticia
    0.41
    น
    0.41
    Activations Density 0.000%

    No Known Activations