© 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-16K
    7. 11710
    Prev
    Next
    INDEX
    Explanations

    filed under or tagged with

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

    would allow, would integrate

    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_16k_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
    Lost
    0.45
    CTL
    0.44
    Logistic
    0.44
     molds
    0.43
     ঘটনা
    0.43
    BESCHREIBUNG
    0.43
     longevity
    0.43
     फ
    0.42
     miRNA
    0.42
    shovel
    0.41
    POSITIVE LOGITS
     preocupación
    0.51
     redact
    0.48
    痘
    0.48
     gobier
    0.48
     Capítulo
    0.48
     dí
    0.47
     práctico
    0.46
     질문
    0.46
    ဖြေ
    0.46
     Hubert
    0.46
    Activations Density 0.003%

    No Known Activations