© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168357
    Prev
    Next
    INDEX
    Explanations

    English token approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downsides
    0.50
     undermined
    0.44
     downregulation
    0.44
    ={"
    0.43
     undermining
    0.43
     immun
    0.42
     shameful
    0.42
     immunosupp
    0.42
    🩹
    0.42
     stereotypes
    0.42
    POSITIVE LOGITS
    و
    0.50
    o
    0.48
    directional
    0.46
    리
    0.46
    i
    0.45
    lake
    0.44
    conex
    0.44
    제
    0.43
    모
    0.42
    follow
    0.42
    Activations Density 0.003%

    No Known Activations