© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 223196
    Prev
    Next
    INDEX
    Explanations

    social cognition and long-tail keywords

    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
     પાર્
    0.43
    ਕਾਰੀ
    0.42
     অভিষ
    0.42
    全民
    0.41
    }.")
    0.40
    Caller
    0.40
    aleb
    0.40
     обо
    0.39
    亜
    0.39
    小さ
    0.39
    POSITIVE LOGITS
     ended
    0.45
    ends
    0.40
     explanatory
    0.39
     continued
    0.39
     twos
    0.38
     feel
    0.37
     ends
    0.37
     생각을
    0.37
    ',
    0.36
     yells
    0.36
    Activations Density 0.000%

    No Known Activations