© 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. 116296
    Prev
    Next
    INDEX
    Explanations

    mounting rod

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

    alternative, fun, different

    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
     reprieve
    0.50
    ्रोल
    0.46
     інших
    0.44
     dvije
    0.44
    चलिए
    0.42
     napis
    0.42
    ⟹
    0.42
    ଡ
    0.41
    のために
    0.40
     преди
    0.40
    POSITIVE LOGITS
    t
    0.45
    prism
    0.45
    tochrome
    0.44
    pill
    0.43
    variance
    0.43
    waste
    0.41
     متخصص
    0.41
     consumption
    0.41
    copter
    0.41
    c
    0.39
    Activations Density 0.000%

    No Known Activations