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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17144
    Prev
    Next
    INDEX
    Explanations

    privacy concerns

    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_65k_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
    isnan
    0.44
     сейчас
    0.42
    PostMapping
    0.41
     सीतारमण
    0.40
    廬
    0.40
    alyse
    0.40
    //
    0.40
    杳
    0.40
     आणि
    0.39
     vat
    0.39
    POSITIVE LOGITS
    怯
    0.48
     zusätzlichen
    0.48
     더욱
    0.47
     supplémentaires
    0.44
     inicialmente
    0.44
     Enhancement
    0.43
     추가
    0.43
     Militar
    0.43
     أكثر
    0.43
     äußerst
    0.43
    Activations Density 0.060%

    No Known Activations