© 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. 4906
    Prev
    Next
    INDEX
    Explanations

    militar fortnightly regarding content

    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
    琚
    0.44
     Vaill
    0.43
    ะไร
    0.43
    คือ
    0.42
     browserSync
    0.41
    OutputDir
    0.41
     Pill
    0.41
     Bigg
    0.41
    ือน
    0.40
     السيارة
    0.40
    POSITIVE LOGITS
    ă
    0.52
    done
    0.48
    患者
    0.46
     त्याच्या
    0.46
     dupa
    0.44
     pazienti
    0.44
    x
    0.43
    dated
    0.43
     pacientes
    0.43
    媚
    0.42
    Activations Density 0.010%

    No Known Activations