© 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. 162782
    Prev
    Next
    INDEX
    Explanations

    describing services and procedures

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

    Samurai, immediately, Yourself

    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
    બાદ
    0.55
     учащихся
    0.53
    రాజు
    0.51
    മാണ
    0.49
    滇
    0.49
     После
    0.49
    চন্দ্রের
    0.48
    velyan
    0.48
     игроков
    0.48
     বাংলাদেশী
    0.47
    POSITIVE LOGITS
     discontinuation
    0.49
     threatening
    0.46
    array
    0.45
     normal
    0.43
     prostitution
    0.43
     coping
    0.43
     typology
    0.42
    𝘇
    0.42
     array
    0.42
    purpose
    0.41
    Activations Density 0.000%

    No Known Activations