© 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. 41595
    Prev
    Next
    INDEX
    Explanations

    completed, improved, security, increased, optimized

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

    colon followed by bullet point or tag

    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
    ⴻ
    0.47
    Lets
    0.47
     Lets
    0.43
    Let
    0.43
     partake
    0.42
     citizenry
    0.42
     demise
    0.42
    ෙ
    0.42
     resurrect
    0.42
    Đi
    0.41
    POSITIVE LOGITS
    ating
    0.46
    eae
    0.45
    amers
    0.45
    arguments
    0.43
    üng
    0.43
    ates
    0.42
    }_{+}^{
    0.42
    infs
    0.40
    如果有
    0.40
    dropout
    0.40
    Activations Density 0.000%

    No Known Activations