© 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. 204082
    Prev
    Next
    INDEX
    Explanations

    finding suitable replacements

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

    geometric and mathematical terms

    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
     Odds
    0.49
     бума
    0.48
     Beside
    0.47
     चीज़
    0.46
     Tote
    0.46
     आपण
    0.46
    粿
    0.46
     قم
    0.46
     Cruise
    0.45
     Refining
    0.45
    POSITIVE LOGITS
     cuadrados
    0.55
     adversely
    0.48
    阻
    0.45
    平方
    0.45
     melhores
    0.44
    amsa
    0.43
    は
    0.43
     asserts
    0.42
     lanes
    0.42
    zyła
    0.42
    Activations Density 0.000%

    No Known Activations