© 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. 100191
    Prev
    Next
    INDEX
    Explanations

    numbers and connections

    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
     calcio
    0.48
     inputted
    0.45
     optimally
    0.45
    }|^{
    0.44
     our
    0.44
     permeate
    0.44
     captured
    0.43
     emigrated
    0.43
     confi
    0.42
     expertly
    0.42
    POSITIVE LOGITS
    2
    0.75
    3
    0.59
    4
    0.59
    1
    0.48
    5
    0.48
    釁
    0.48
     दोन
    0.47
    AL
    0.45
    ownership
    0.45
    equality
    0.44
    Activations Density 0.006%

    No Known Activations