© 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. 95059
    Prev
    Next
    INDEX
    Explanations

    pieces of a whole

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

    part of a whole

    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
     безу
    0.47
     воспомина
    0.46
    簟
    0.43
     tagline
    0.42
    อล
    0.41
     GÉN
    0.41
     оформ
    0.41
    传来
    0.41
     retrait
    0.40
     جایی
    0.40
    POSITIVE LOGITS
    fraction
    0.43
     futures
    0.43
     societies
    0.42
    ;
    0.42
    networks
    0.41
     gases
    0.41
    paths
    0.41
     also
    0.40
    scale
    0.40
     escala
    0.40
    Activations Density 0.001%

    No Known Activations