© 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. 35988
    Prev
    Next
    INDEX
    Explanations

    detailed steps, build, consume

    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
    ем
    0.49
    ен
    0.48
    濤
    0.47
    addGroup
    0.46
    ко
    0.45
    ポー
    0.45
     objString
    0.45
     Mainly
    0.43
    햐
    0.43
     mainly
    0.43
    POSITIVE LOGITS
     कोणताही
    0.46
     before
    0.45
    than
    0.45
     Before
    0.45
     是
    0.44
     Retrieved
    0.43
     ಬಾ
    0.43
     قبل
    0.43
     পারলে
    0.43
    aan
    0.43
    Activations Density 0.002%

    No Known Activations