© 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. 95376
    Prev
    Next
    INDEX
    Explanations

    electronic file recipients

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

    instructions for actions or states

    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
    kommt
    0.54
    简称
    0.53
    하루
    0.52
     Duf
    0.49
    협
    0.48
    кали
    0.47
    젤
    0.47
    细菌
    0.47
    commonly
    0.46
    filament
    0.46
    POSITIVE LOGITS
     showcasing
    0.51
     amelior
    0.46
    inase
    0.46
     mashed
    0.45
     arial
    0.45
     crippling
    0.44
     overly
    0.43
    ianos
    0.43
     eradic
    0.42
     compensated
    0.42
    Activations Density 0.001%

    No Known Activations