© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 191525
    Prev
    Next
    INDEX
    Explanations

    layoffs in tech companies

    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_40_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
     ghost
    0.37
     blueprint
    0.36
    펴
    0.35
    removeAttribute
    0.35
    聴
    0.35
     laboratorium
    0.34
     bureaucracy
    0.34
    برا
    0.34
     froze
    0.33
    听
    0.33
    POSITIVE LOGITS
     ಹಲವಾರು
    0.42
     inspiración
    0.42
     شم
    0.40
     enumerable
    0.40
    ڑے
    0.40
     வகையான
    0.40
     तरह
    0.39
    romad
    0.39
    ciparum
    0.39
     groei
    0.39
    Activations Density 0.000%

    No Known Activations