© 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. 73021
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases

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

    lacking and unconscious states

    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
     कट्टर
    0.54
     любят
    0.52
     પણ
    0.52
     любит
    0.50
    ırs
    0.49
    どんどん
    0.49
    细腻
    0.49
    缛
    0.49
     سرطان
    0.47
    iennent
    0.47
    POSITIVE LOGITS
     resting
    0.47
     parking
    0.46
     governmental
    0.44
     rainwater
    0.44
     notwithstanding
    0.42
     preparatory
    0.42
     occasioned
    0.42
     canteen
    0.42
     lacked
    0.41
     meteorological
    0.41
    Activations Density 0.004%

    No Known Activations