© 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. 32969
    Prev
    Next
    INDEX
    Explanations

    things decreasing over time

    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
     .
    0.43
     bus
    0.43
    驚
    0.43
     Bus
    0.42
     emerald
    0.42
    彼は
    0.41
     Cooking
    0.40
     From
    0.39
     jossa
    0.39
    ↵
    0.39
    POSITIVE LOGITS
    entionally
    0.52
    ante
    0.49
    ocl
    0.49
    ahun
    0.48
    ceptive
    0.47
    atonic
    0.46
    ieuse
    0.46
    ak
    0.46
    ikl
    0.45
    otechnical
    0.45
    Activations Density 0.002%

    No Known Activations