Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 3339
    Prev
    Next
    INDEX
    Explanations

    to the

    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_40_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
    .
    0.32
    a
    0.31
    '
    0.29
    ’
    0.27
     gleichen
    0.25
    l
    0.25
    n
    0.25
     in
    0.24
    	
    0.23
    s
    0.23
    POSITIVE LOGITS
    ppled
    0.47
     the
    0.40
    ppling
    0.34
     perpetuate
    0.33
     amazement
    0.31
     appease
    0.31
     include
    0.31
     fruition
    0.30
     what
    0.29
     illustrate
    0.29
    Activations Density 0.206%

    No Known Activations