© 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. 61388
    Prev
    Next
    INDEX
    Explanations

    personal relationships and states

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

    federated generative networks

    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
    无
    0.48
    рон
    0.44
    大
    0.44
    移
    0.43
    元素的
    0.43
    力量
    0.43
    日
    0.43
    齐全
    0.42
    妬
    0.42
    icals
    0.42
    POSITIVE LOGITS
     رو
    0.49
     eril
    0.46
     potem
    0.46
     ro
    0.45
     sekitar
    0.45
     로
    0.44
     PGR
    0.44
     beberapa
    0.44
     savo
    0.44
     cinder
    0.43
    Activations Density 0.000%

    No Known Activations