© 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-16K
    4. 1306
    Prev
    Next
    INDEX
    Explanations

    low cost offers

    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
     various
    0.67
     regular
    0.66
     overall
    0.64
     
    0.64
     currently
    0.63
     us
    0.61
     |
    0.60
     tarafından
    0.60
     [
    0.59
     notable
    0.58
    POSITIVE LOGITS
     Jangan
    1.12
    Simplify
    1.11
     Simplify
    1.10
     frivol
    1.08
    哪怕
    1.05
     simplify
    1.03
    Jangan
    1.01
    simplify
    1.00
     Même
    0.98
     jangan
    0.97
    Activations Density 1.080%

    No Known Activations