© 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. 44386
    Prev
    Next
    INDEX
    Explanations

    retain money for protests

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

    section titles and symbols

    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
    VR
    0.47
    С
    0.43
    Σ
    0.43
    æ
    0.42
    Viki
    0.42
    ,$
    0.40
    angements
    0.40
    ﾅ
    0.40
    חס
    0.39
    Rajas
    0.39
    POSITIVE LOGITS
     आला
    0.42
     Innovative
    0.42
    সাল
    0.42
     வந்தால்
    0.41
    の中でも
    0.41
    ে
    0.41
     अग्रणी
    0.40
     gelegt
    0.40
     ہمیشہ
    0.39
     όλ
    0.39
    Activations Density 0.000%

    No Known Activations