© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 470
    Prev
    Next
    INDEX
    Explanations

    foreign country, skills, empowerment

    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_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
     squeezed
    1.10
    ी
    1.10
     prune
    1.09
    म
    1.07
    uette
    1.06
    iagnosed
    1.05
    odend
    1.05
    ح
    1.04
     badi
    1.04
     شوند
    1.02
    POSITIVE LOGITS
     empowerment
    1.15
     emancipation
    1.10
     protes
    1.08
     Empower
    1.08
    в
    1.08
     empir
    1.08
    nof
    1.07
     règle
    1.07
    pour
    1.07
     spoilers
    1.05
    Activations Density 0.000%

    No Known Activations