© 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. 189870
    Prev
    Next
    INDEX
    Explanations

    cost of a wound

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

    paying extra, older script, Data Interpretation

    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
    asers
    0.50
    гти
    0.47
    řit
    0.47
    𝚞
    0.46
     লাখ
    0.46
     लाख
    0.45
     Bare
    0.44
     cambiado
    0.44
    જબ
    0.43
     ભાગ
    0.43
    POSITIVE LOGITS
    iness
    0.45
     befri
    0.43
    était
    0.42
    ồn
    0.42
     კი
    0.42
    openqa
    0.41
    toLowerCase
    0.40
    getPassword
    0.40
    鐟
    0.40
     oub
    0.40
    Activations Density 0.000%

    No Known Activations