© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1611
    Prev
    Next
    INDEX
    Explanations

    offset, new, Greece, upon request, every, Evangel

    np_acts-logits-general · gemini-2.5-flash-lite

    Greek and Greece

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ണേ
    0.46
    يهه
    0.44
    궂
    0.43
    निश्ड
    0.43
     shouldUse
    0.42
    тическая
    0.42
    splitLength
    0.42
     уйный
    0.41
     الطلبه
    0.41
    य्
    0.41
    POSITIVE LOGITS
     Α
    1.49
     Τ
    1.48
     Μ
    1.45
     Κ
    1.45
     Ε
    1.42
     Ν
    1.40
     Β
    1.40
     Ι
    1.40
     Thessaloniki
    1.38
    Τ
    1.34
    Activations Density 0.182%

    No Known Activations