© 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. 31-GEMMASCOPE-2-RES-262K
    4. 170005
    Prev
    Next
    INDEX
    Explanations

    Craigslist local sales

    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_31_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
    
    0.48
    
    0.47
     zwölf
    0.47
    苯
    0.45
     adultos
    0.44
     hypertro
    0.44
     квар
    0.43
     amic
    0.43
    symmetry
    0.43
     altri
    0.43
    POSITIVE LOGITS
     has
    0.59
     and
    0.46
     Knowledge
    0.45
    蒖
    0.45
     Nest
    0.44
     Security
    0.42
    粦
    0.42
     Automation
    0.42
     Accounting
    0.41
    紧
    0.41
    Activations Density 0.002%

    No Known Activations