© 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-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36747
    Prev
    Next
    INDEX
    Explanations

    foreign characters and instructional steps

    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
    }(\
    0.43
    ண்ப
    0.43
     Univ
    0.42
     Click
    0.42
     timeline
    0.41
     Shah
    0.41
     sacrifices
    0.41
     is
    0.41
    ן
    0.41
     cutoff
    0.40
    POSITIVE LOGITS
    .'),
    0.46
    !(
    0.44
     유명
    0.43
    ()}')
    0.42
     био
    0.41
    一本
    0.41
    .')
    0.40
    !';
    0.40
    :'],
    0.40
    礬
    0.40
    Activations Density 0.000%

    No Known Activations