© 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. 17241
    Prev
    Next
    INDEX
    Explanations

    console commands

    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
     In
    0.50
     The
    0.47
     Test
    0.41
     sure
    0.40
     For
    0.39
     A
    0.39
     An
    0.38
     जानिए
    0.38
     Focus
    0.38
    i
    0.37
    POSITIVE LOGITS
     sarcom
    0.46
     hydroly
    0.44
     hydrolysis
    0.43
    Callories
    0.42
     spores
    0.42
    Prothorax
    0.41
    LensFlare
    0.41
    Gosudarstvennyj
    0.41
     isotherm
    0.40
    OLYBD
    0.40
    Activations Density 0.459%

    No Known Activations