© 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. 238553
    Prev
    Next
    INDEX
    Explanations

    selected from, service of, deprive oneself

    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
    缡
    0.47
    订阅
    0.46
    ώσει
    0.44
    翱
    0.43
     σχέ
    0.43
    莼
    0.42
     ሙሉ
    0.41
    에서의
    0.41
    经验
    0.40
     законодав
    0.40
    POSITIVE LOGITS
     Fácil
    0.48
     underprivileged
    0.48
     Preto
    0.46
     お
    0.46
     mumbled
    0.46
     incap
    0.45
     Jako
    0.45
     Barbosa
    0.44
     overpriced
    0.43
     Moura
    0.43
    Activations Density 0.001%

    No Known Activations