© 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. 97724
    Prev
    Next
    INDEX
    Explanations

    fitted, designated, indicating, creating, secure

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

    capacity and change

    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
    ow
    0.55
    idea
    0.55
    va
    0.54
    ↵
    0.52
    ang
    0.52
    ist
    0.51
    ja
    0.49
    ika
    0.48
    je
    0.48
    ost
    0.48
    POSITIVE LOGITS
    كة
    0.52
    ৫৫
    0.51
    OUTH
    0.50
     容量
    0.49
    ৫৪
    0.47
    INAL
    0.47
    菘
    0.46
    速率
    0.46
    AtPath
    0.45
    Capacity
    0.45
    Activations Density 0.010%

    No Known Activations