© 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. 16633
    Prev
    Next
    INDEX
    Explanations

    URL, phrases, requirements

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

    such AI abilities

    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
     細胞
    0.36
    த்தின்
    0.34
    _
    0.33
     黃
    0.33
    *,
    0.33
     ইতো
    0.33
    ombok
    0.33
    ʼ
    0.32
     уйнарга
    0.32
    propan
    0.32
    POSITIVE LOGITS
     tantos
    0.50
     tantas
    0.49
     이런
    0.46
     slike
    0.46
     nicer
    0.45
     ilyen
    0.45
    这么
    0.45
     solche
    0.44
     এতটা
    0.44
    这么多
    0.43
    Activations Density 0.000%

    No Known Activations