© 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. 58506
    Prev
    Next
    INDEX
    Explanations

    private entities and services

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

    private, public, protected modifiers

    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
    ţ
    0.56
    ъз
    0.50
     directional
    0.48
    ানার
    0.46
     direcion
    0.45
     radiator
    0.44
    uch
    0.43
     indicar
    0.43
     handout
    0.43
     receding
    0.42
    POSITIVE LOGITS
    '
    0.46
     etapa
    0.44
     打
    0.44
     části
    0.44
    Priv
    0.41
     অপরাধ
    0.40
    фі
    0.40
     Pří
    0.40
    Бі
    0.39
    音
    0.39
    Activations Density 0.005%

    No Known Activations