© 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. 79467
    Prev
    Next
    INDEX
    Explanations

    understanding, proud, waterproof, gene, God

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

    moral consideration and wildflowers

    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
     dola
    0.46
     quals
    0.44
     birl
    0.44
     maks
    0.43
    डिंग
    0.43
     lainnya
    0.43
     nawet
    0.42
    ]
    0.42
    ژ
    0.42
    黯
    0.42
    POSITIVE LOGITS
     環
    0.53
    GetComponent
    0.47
    Fmat
    0.47
    喚
    0.47
    iterations
    0.46
    intrinsic
    0.46
    защи
    0.46
    fänger
    0.45
    SourceIP
    0.44
    controls
    0.44
    Activations Density 0.000%

    No Known Activations