© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    political critiques, historical context

    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
    0.89
     Re
    0.86
     N
    0.85
     Ch
    0.82
     timings
    0.82
     Be
    0.82
     B
    0.80
     Lo
    0.80
     D
    0.78
     Pre
    0.78
    POSITIVE LOGITS
    inairement
    1.42
    owanego
    1.33
    ómago
    1.31
    issaient
    1.30
    ellschaft
    1.30
    endorong
    1.30
    initro
    1.29
    abhave
    1.29
    <unused1022>
    1.28
    ździer
    1.28
    Activations Density 0.001%

    No Known Activations