© 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. 223879
    Prev
    Next
    INDEX
    Explanations

    brand channel

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

    educational, children, or technical contexts

    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
    telefone
    0.42
    ismer
    0.42
    ációs
    0.41
     బాధ
    0.41
     Saya
    0.41
     React
    0.40
    ్రు
    0.40
    墘
    0.40
     Folge
    0.39
     Fruit
    0.39
    POSITIVE LOGITS
    Packed
    0.52
     símbolo
    0.50
     emotes
    0.48
     dédiée
    0.48
     stallions
    0.43
     escorted
    0.43
     مسلح
    0.43
     فوج
    0.42
     симво
    0.41
     públicas
    0.41
    Activations Density 0.000%

    No Known Activations