© 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. 59593
    Prev
    Next
    INDEX
    Explanations

    preparing for purpose

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

    case for basic

    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
     substance
    0.44
     गण
    0.43
     manj
    0.43
     —
    0.42
     Substance
    0.42
    ulka
    0.42
     elderly
    0.41
     Examiner
    0.40
     Arora
    0.40
     Croatian
    0.40
    POSITIVE LOGITS
     বাড়ির
    0.54
    fab
    0.48
    砝
    0.46
    গি
    0.46
     bőr
    0.46
    电机
    0.46
     gyárt
    0.46
    quées
    0.45
    鸯
    0.44
    Oe
    0.43
    Activations Density 0.000%

    No Known Activations