© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1600
    Prev
    Next
    INDEX
    Explanations

    dialogue starts with punctuation or names

    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_16k_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
     disponibil
    1.16
     различных
    1.05
    㐱
    1.02
    㤈
    1.01
     Татьяна
    1.01
     thereon
    1.00
     encontrada
    1.00
    \".
    1.00
    㐰
    0.99
     realizada
    0.99
    POSITIVE LOGITS
     heavy
    0.71
     mass
    0.69
     Sp
    0.67
     দৃঢ়
    0.64
    毫无
    0.63
    简直
    0.63
     decisive
    0.63
     legal
    0.62
     alien
    0.62
     Critics
    0.62
    Activations Density 0.007%

    No Known Activations