© 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. 231713
    Prev
    Next
    INDEX
    Explanations

    automotive mount, System Repair Disc

    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
    িও
    0.53
     Munich
    0.48
     フランス
    0.47
    {'
    0.46
    رخ
    0.44
    ael
    0.44
    zd
    0.43
     reconciliation
    0.43
     कॉन्फ्रेंस
    0.43
    ಗೊಳ್ಳ
    0.43
    POSITIVE LOGITS
     અવ
    0.45
     pinpoint
    0.45
    väl
    0.44
     గ
    0.43
     여기에
    0.43
     zusätzlich
    0.43
     adjustable
    0.42
     vielf
    0.42
     voraus
    0.42
     persisting
    0.42
    Activations Density 0.000%

    No Known Activations