© 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. 199653
    Prev
    Next
    INDEX
    Explanations

    experience profile, wood stoves, read this, invitation messages

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

    access to specific entities

    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
     トレー
    0.49
     Maas
    0.48
     FDR
    0.46
     を
    0.46
     ≈
    0.46
     toes
    0.45
     フラ
    0.45
     Sasaki
    0.45
     sopr
    0.45
     kurs
    0.45
    POSITIVE LOGITS
    धुनिक
    0.44
    chemist
    0.43
    PageComponent
    0.43
    вающая
    0.42
    does
    0.42
    racing
    0.42
    一丝
    0.42
    ckte
    0.42
     আশ্চর্য
    0.42
    튕
    0.42
    Activations Density 0.003%

    No Known Activations