© 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. 100407
    Prev
    Next
    INDEX
    Explanations

    designs and operation

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

    factors and levels

    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
    Penny
    0.43
    Piano
    0.43
    Swan
    0.43
    Laugh
    0.42
     tourne
    0.41
     kinder
    0.41
     overruled
    0.41
    償
    0.41
    眩
    0.41
    Lamp
    0.41
    POSITIVE LOGITS
     เนื่องจาก
    0.53
     após
    0.51
     після
    0.51
     إذا
    0.48
     جدید
    0.48
     Modify
    0.48
    :'.
    0.48
     अरे
    0.47
     Após
    0.47
    :,
    0.47
    Activations Density 0.000%

    No Known Activations