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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7490
    Prev
    Next
    INDEX
    Explanations

    secrets and hidden things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    땠
    0.79
     detail
    0.70
     செலு
    0.70
     phenotype
    0.68
    僉
    0.67
     proudly
    0.66
     uniformly
    0.65
     Areas
    0.65
     postérieur
    0.65
     cytoplasmic
    0.65
    POSITIVE LOGITS
     secrets
    1.27
     adventures
    1.20
    secrets
    1.12
    Secrets
    1.11
     perils
    1.11
     Secrets
    1.11
     conspiracies
    1.10
     uncovering
    1.10
    捲
    1.09
     jeopard
    1.09
    Activations Density 0.190%

    No Known Activations