© 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. 126683
    Prev
    Next
    INDEX
    Explanations

    prevent further escalation or risk

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

    supply chains, transaction logs, or gas

    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
     不需要
    0.56
     taxation
    0.52
     trusts
    0.49
     Linux
    0.48
     taxing
    0.47
     √
    0.47
     actuators
    0.47
     Mrs
    0.46
     reserves
    0.46
     subcut
    0.45
    POSITIVE LOGITS
    ہ
    0.59
     mezcla
    0.54
     Marcelo
    0.51
    Der
    0.49
    Avec
    0.48
     öss
    0.48
     jogador
    0.48
    Vij
    0.48
    हेज
    0.47
    ﻘ
    0.47
    Activations Density 0.000%

    No Known Activations