© 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-262K
    7. 77074
    Prev
    Next
    INDEX
    Explanations

    block, enhances, feeling, molecules, output

    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_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
    楸
    0.49
     meningkat
    0.48
     syarat
    0.48
     poważ
    0.48
     -\
    0.47
    šit
    0.46
     rozpoczę
    0.46
    انی
    0.45
     Hrvats
    0.45
     แสดง
    0.45
    POSITIVE LOGITS
    vale
    0.44
    9
    0.44
     confined
    0.44
    acht
    0.43
    chemical
    0.43
    amanho
    0.43
    న్యూ
    0.42
    填充
    0.41
     الخامس
    0.41
     کھل
    0.40
    Activations Density 0.000%

    No Known Activations