© 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. 173506
    Prev
    Next
    INDEX
    Explanations

    brain, mental states, or brainstorming

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

    brain development

    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
    п
    0.64
    ang
    0.63
    isPrime
    0.61
    Ibid
    0.59
    めに
    0.59
    kali
    0.58
    läuft
    0.58
    doesn
    0.58
    ま
    0.58
    И
    0.58
    POSITIVE LOGITS
     brain
    1.07
     Brain
    1.01
     brainstorming
    0.96
     cerebr
    0.96
     cerebral
    0.86
     brains
    0.84
     cervello
    0.84
     mind
    0.82
    🧠
    0.82
     моз
    0.81
    Activations Density 0.196%

    No Known Activations