© 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. 18084
    Prev
    Next
    INDEX
    Explanations

    keep, follow, prevent, need

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

    understanding, describing, or asking about concepts

    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
    "،
    0.49
    ،
    0.47
    )،
    0.47
    ”،
    0.46
     सिंगिंग
    0.46
     demonstr
    0.46
     フラワー
    0.45
    گار
    0.45
    شاد
    0.45
     demostrar
    0.44
    POSITIVE LOGITS
    น
    0.50
    นม
    0.49
    本社
    0.49
    ন
    0.47
    μ
    0.47
    মু
    0.46
    र
    0.45
    હ
    0.44
    nuget
    0.42
    ಳಿಗೆ
    0.41
    Activations Density 0.000%

    No Known Activations