© 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. 56934
    Prev
    Next
    INDEX
    Explanations

    people will do

    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
     horsepower
    0.42
     hometown
    0.42
     grasp
    0.42
    }}=
    0.41
     विशेषताओं
    0.40
    redit
    0.38
    GREAT
    0.38
    produce
    0.38
    馭
    0.38
    ilí
    0.38
    POSITIVE LOGITS
     chiede
    0.59
     solcher
    0.47
     ailleurs
    0.46
     কিংবা
    0.45
     éventuellement
    0.44
     faisait
    0.44
     chiese
    0.44
     chied
    0.44
     refusing
    0.43
     chiesto
    0.43
    Activations Density 0.014%

    No Known Activations