© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5258
    Prev
    Next
    INDEX
    Explanations

    contrast before officials or progress

    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_65k_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
     ഞാന്‍
    0.85
     мою
    0.82
     എന്റെ
    0.79
     ഞാൻ
    0.78
     सदैव
    0.78
     my
    0.76
     =
    0.76
    ς
    0.75
     moim
    0.75
    sometimes
    0.75
    POSITIVE LOGITS
     officials
    2.11
     analysts
    1.95
     experts
    1.92
     investigators
    1.84
     researchers
    1.80
     lawmakers
    1.77
     activists
    1.72
    Officials
    1.71
     organizers
    1.70
    experts
    1.67
    Activations Density 0.017%

    No Known Activations