© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14318
    Prev
    Next
    INDEX
    Explanations

    molecules, chemical, proteins, DNA

    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_16_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
     invented
    0.57
    方形
    0.50
    父
    0.48
    つけて
    0.47
     en
    0.45
    さい
    0.44
    жного
    0.44
    ץ
    0.44
     JAN
    0.43
    廠商
    0.43
    POSITIVE LOGITS
    Fhir
    0.60
    ğinin
    0.58
     proteínas
    0.57
     demás
    0.56
    h
    0.55
     materias
    0.55
    Ils
    0.55
     Proteins
    0.54
     questão
    0.54
     leurs
    0.53
    Activations Density 0.017%

    No Known Activations