© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 671
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    ᔨ
    1.06
     좋을
    1.01
     المت
    1.01
    тил
    1.00
     Kategor
    0.99
     Antes
    0.99
    に適
    0.99
    ne
    0.99
    րա
    0.97
    iben
    0.97
    POSITIVE LOGITS
    frameCount
    1.03
     ­
    0.98
    cor
    0.96
     hacks
    0.95
    Hungary
    0.93
    oncé
    0.93
     Yuan
    0.89
    And
    0.88
     Obamacare
    0.87
     plung
    0.87
    Activations Density 0.000%

    No Known Activations