© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1995
    Prev
    Next
    INDEX
    Explanations

    introducing clauses

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

    which can

    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
     เลือก
    0.23
     বৃহত্তম
    0.21
    เลือก
    0.20
    𝙷
    0.20
    鐧
    0.20
     निरीक्षण
    0.20
     creando
    0.20
    }$.
    0.20
     tasma
    0.20
     There
    0.20
    POSITIVE LOGITS
     incidentally
    0.46
     কিনা
    0.40
     was
    0.37
     heretofore
    0.36
     ironically
    0.36
     wasn
    0.35
     unfortunately
    0.35
     resulted
    0.33
     although
    0.33
     hopefully
    0.33
    Activations Density 0.558%

    No Known Activations