© 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. 36038
    Prev
    Next
    INDEX
    Explanations

    inherent cultural

    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
    Black
    0.44
    Inside
    0.43
     that
    0.40
    chemist
    0.40
    +
    0.40
     rhet
    0.39
    Sac
    0.39
     rhetorical
    0.39
    original
    0.39
     calm
    0.38
    POSITIVE LOGITS
    ścic
    0.51
    τεί
    0.47
     abut
    0.45
     IconButton
    0.44
    Ữ
    0.43
    utacji
    0.42
     radioButton
    0.42
    ্কে
    0.42
     localObject
    0.42
     Επι
    0.42
    Activations Density 0.002%

    No Known Activations