© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16205
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     administrativos
    -0.96
     userDao
    -0.96
     updateUser
    -0.95
    €/
    -0.94
    手掌
    -0.94
    💕
    -0.93
    🔥🔥
    -0.93
    quis
    -0.92
    llllll
    -0.91
    💚
    -0.91
    POSITIVE LOGITS
    ⠝
    1.13
    erkek
    0.97
     encarga
    0.93
     Latter
    0.92
     décret
    0.92
    Szer
    0.91
    flowering
    0.91
    ेड
    0.90
     manualidades
    0.89
    ָל
    0.89
    Activations Density 0.004%

    No Known Activations