© 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. 197607
    Prev
    Next
    INDEX
    Explanations

    introduces a subject or title

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

    positive comments and reviews

    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
     농
    0.54
     ""`
    0.45
     ти
    0.43
    ⌇
    0.43
     λέ
    0.42
     !",
    0.42
     치
    0.41
     አለ
    0.41
    치가
    0.41
     букмекерлер
    0.41
    POSITIVE LOGITS
    DC
    0.44
    vspace
    0.44
    .
    0.43
    gets
    0.42
    notes
    0.42
    interesting
    0.42
    academic
    0.41
    features
    0.41
    Design
    0.41
    PIC
    0.41
    Activations Density 0.010%

    No Known Activations