© 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. 238797
    Prev
    Next
    INDEX
    Explanations

    series of, County of, note that

    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
    راه
    0.45
    戻
    0.45
    ills
    0.44
     hypers
    0.42
     superstitious
    0.42
     sensitive
    0.41
     linger
    0.41
    焼け
    0.41
    残
    0.41
    iders
    0.40
    POSITIVE LOGITS
     அனும
    0.55
     ના
    0.52
     Literatur
    0.51
     Interactions
    0.50
     Ausstattung
    0.47
     Playing
    0.46
    스는
    0.46
     Transporte
    0.46
     Js
    0.46
     Plugging
    0.46
    Activations Density 0.000%

    No Known Activations