© 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. 115985
    Prev
    Next
    INDEX
    Explanations

    promises, visits, great features

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

    non-english words

    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
     def
    0.45
     futile
    0.45
     iron
    0.44
     ▲
    0.44
     abstinence
    0.43
     biologists
    0.43
     fracking
    0.43
     prostitutes
    0.43
     hemicontinuous
    0.43
     plasmids
    0.42
    POSITIVE LOGITS
    rische
    0.50
    और
    0.49
    ❣️
    0.48
    მართ
    0.47
    КА
    0.46
    ருக்கு
    0.44
    के
    0.44
    ளுக்கான
    0.44
     என்க
    0.43
    functie
    0.43
    Activations Density 0.000%

    No Known Activations