© 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. 249609
    Prev
    Next
    INDEX
    Explanations

    words like 'or', 'biogas', 'use', 'wish', 'Overnight', 'necessary', 'wanted'

    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
     radic
    0.50
     سلام
    0.46
    育て
    0.45
     سلامه
    0.44
     betrayed
    0.43
     दिले
    0.43
    섦
    0.43
    略
    0.43
    聸
    0.43
     bred
    0.42
    POSITIVE LOGITS
    ан
    0.48
     pudi
    0.46
    سان
    0.45
    ittäin
    0.45
     utilizzando
    0.45
    िएंट
    0.44
    ッター
    0.44
     ensayo
    0.44
     Utilizing
    0.43
    of
    0.43
    Activations Density 0.000%

    No Known Activations