© 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. 20698
    Prev
    Next
    INDEX
    Explanations

    water purifier

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

    Temporal dynamics, proposed time, explanations

    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
    áculo
    0.50
     Londres
    0.48
     partially
    0.47
     somewhat
    0.45
    áculos
    0.45
     downfall
    0.45
    ú
    0.44
    apath
    0.43
    ções
    0.43
    acciones
    0.43
    POSITIVE LOGITS
    Dimethyl
    0.49
    Intensity
    0.48
    디오
    0.47
    教练
    0.47
    Delta
    0.46
    蜞
    0.46
    ТС
    0.45
    Discrimin
    0.45
    Scheduling
    0.45
    КА
    0.44
    Activations Density 0.000%

    No Known Activations