© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8807
    Prev
    Next
    INDEX
    Explanations

    self-talk about self-worth and capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
     the
    0.92
    4
    0.88
     large
    0.82
    8
    0.81
     by
    0.79
     use
    0.77
     include
    0.77
    使用
    0.77
    2
    0.76
    7
    0.76
    POSITIVE LOGITS
     meinem
    1.38
     Myself
    1.38
     estoy
    1.37
     زندگی
    1.34
     నాకు
    1.32
     인생
    1.31
     ನನ್ನ
    1.30
    我现在
    1.30
     empecé
    1.30
     আমার
    1.29
    Activations Density 0.002%

    No Known Activations