© 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. 31-GEMMASCOPE-2-RES-65K
    7. 20269
    Prev
    Next
    INDEX
    Explanations

    APIs, data, rate

    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_65k_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
    utors
    0.55
    úl
    0.47
     極
    0.47
    MiddleLine
    0.47
     reglas
    0.46
     calamities
    0.45
     excepciones
    0.45
     اختی
    0.45
    極
    0.45
    ура
    0.44
    POSITIVE LOGITS
     aonde
    0.48
    បាន
    0.46
     бере
    0.45
    您
    0.44
    pre
    0.43
     Natal
    0.42
     Trader
    0.42
     Civilization
    0.42
    /**
    0.42
     Dieu
    0.41
    Activations Density 0.003%

    No Known Activations