© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 103558
    Prev
    Next
    INDEX
    Explanations

    "Good Girl" Art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     indented
    0.57
     inferiores
    0.56
     entregar
    0.53
    -
    0.51
     epidemics
    0.49
    lerdir
    0.49
    мато
    0.49
     entendre
    0.49
     быст
    0.49
    増
    0.49
    POSITIVE LOGITS
    ل
    0.76
     an
    0.59
    ল
    0.58
     says
    0.55
     Bick
    0.54
     Eno
    0.52
     talks
    0.52
     Strateg
    0.50
     Andover
    0.49
     Meth
    0.49
    Activations Density 0.000%

    No Known Activations