© 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. 71909
    Prev
    Next
    INDEX
    Explanations

    myself, nothing, too, says, steps, cave

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

    seeing in the dark

    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
     interesados
    0.48
     시절
    0.48
     oyunc
    0.47
    ک
    0.45
     сов
    0.45
     мыкты
    0.44
    ahua
    0.43
    ancı
    0.42
    ској
    0.42
    нер
    0.42
    POSITIVE LOGITS
     Hmm
    0.46
     PRACTICE
    0.45
     bb
    0.45
     tachycardia
    0.44
     जाएं
    0.44
    ᓕ
    0.44
     Different
    0.44
     consolidating
    0.43
    िलं
    0.43
     DEVELOP
    0.43
    Activations Density 0.000%

    No Known Activations