© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    print(f strings

    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_17_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
    ષ
    0.62
    !";
    0.60
    ılmıştır
    0.59
    ();
    0.59
    ংকর
    0.58
     );
    0.57
    深受
    0.56
    梨
    0.55
    Esper
    0.54
    management
    0.53
    POSITIVE LOGITS
    f
    1.14
     f
    1.10
    F
    0.93
     F
    0.92
    Ф
    0.82
    𝙛
    0.82
    fz
    0.81
    fuck
    0.81
    ｆ
    0.80
     frit
    0.80
    Activations Density 0.099%

    No Known Activations