© 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. 91441
    Prev
    Next
    INDEX
    Explanations

    built or created

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

    company registered manager

    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
    ט
    0.45
    тын
    0.45
    ступи
    0.43
    Gina
    0.43
    🥫
    0.43
    らない
    0.42
    สะอาด
    0.41
    🍈
    0.40
    ተኛ
    0.40
    سازی
    0.40
    POSITIVE LOGITS
     dirinya
    0.49
     lekar
    0.49
     legate
    0.48
     fleks
    0.46
     kabel
    0.44
     możli
    0.44
     pukul
    0.44
     gratuita
    0.44
     sebanyak
    0.43
     posl
    0.43
    Activations Density 0.001%

    No Known Activations