© 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. 20686
    Prev
    Next
    INDEX
    Explanations

    generators, basis, vectors, roots

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

    basis vectors generating span

    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
     संभाव
    0.38
    ಿಸುತ್ತದೆ
    0.38
     perceptual
    0.38
    日本では
    0.38
     secretNumber
    0.38
     singapore
    0.37
    섭
    0.37
    шена
    0.37
    邦
    0.36
     attachment
    0.36
    POSITIVE LOGITS
     цент
    0.51
     Pablo
    0.50
     দখল
    0.50
     monomials
    0.48
    atorul
    0.47
     Samp
    0.47
    Abasis
    0.47
    ⓡ,
    0.47
     எலும்
    0.47
    仡
    0.46
    Activations Density 0.000%

    No Known Activations