© 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. 56536
    Prev
    Next
    INDEX
    Explanations

    introduction of self and import statement

    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
    lish
    0.49
    PI
    0.47
    li
    0.45
    高
    0.45
     guided
    0.44
     persons
    0.43
    OG
    0.43
     PPI
    0.43
     mentions
    0.42
    ités
    0.42
    POSITIVE LOGITS
     tartış
    0.49
     ayrıca
    0.46
     Protest
    0.46
    dtypes
    0.45
     احتجاج
    0.45
    норийска
    0.45
     "*************"
    0.44
     डिस्कस
    0.44
     Situated
    0.43
     maquinaria
    0.42
    Activations Density 0.027%

    No Known Activations