© 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. 155289
    Prev
    Next
    INDEX
    Explanations

    general descriptions of actions or states

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

    monitoring conditions and releases

    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
    𝐞
    0.47
    ເ
    0.46
    𝗪
    0.46
    াজ
    0.42
     productService
    0.41
    readLine
    0.41
    𝒂
    0.41
    튼
    0.41
     መሰ
    0.40
    escu
    0.40
    POSITIVE LOGITS
     diharapkan
    0.49
     habrá
    0.47
     impi
    0.47
     administration
    0.45
     reichen
    0.44
     informant
    0.44
    ப்படுகின்றன
    0.44
     diminta
    0.43
     vais
    0.42
     movie
    0.42
    Activations Density 0.001%

    No Known Activations