© 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. 156350
    Prev
    Next
    INDEX
    Explanations

    mathematical diagrams and theory

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

    category theory objects diagrams

    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
     Verteid
    0.53
     Ordn
    0.52
     Ouais
    0.52
     statistique
    0.51
     Portail
    0.48
    𝙃
    0.48
    istisch
    0.47
     ډول
    0.47
    alen
    0.47
     entdecken
    0.47
    POSITIVE LOGITS
    クリー
    0.47
    そろ
    0.45
    ଞ
    0.45
    appointment
    0.44
     aromatic
    0.43
    i
    0.43
    車の
    0.42
    禊
    0.42
     anniversary
    0.41
     unattractive
    0.41
    Activations Density 0.000%

    No Known Activations