© 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. 155146
    Prev
    Next
    INDEX
    Explanations

    objective descriptions and facts

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

    making, allowing, active

    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
    da
    0.63
    s
    0.62
     ล
    0.56
    i
    0.50
    quando
    0.49
    texto
    0.49
    ş
    0.48
    phi
    0.48
    ad
    0.48
     ಕರ್ನಾಟಕ
    0.47
    POSITIVE LOGITS
     prů
    0.47
    编
    0.45
    湫
    0.44
    编制
    0.42
    ཱ
    0.42
     objectively
    0.42
    的研究
    0.41
    客观
    0.41
     baseX
    0.41
    Ⲱ
    0.41
    Activations Density 0.000%

    No Known Activations