© 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. 4948
    Prev
    Next
    INDEX
    Explanations

    broken down into

    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
     विराजमान
    0.63
     hiçbir
    0.62
    Вер
    0.60
     நிலையத்தில்
    0.60
     ningún
    0.59
    стный
    0.58
    shadow
    0.58
    驰
    0.58
    Mientras
    0.58
    Shadow
    0.57
    POSITIVE LOGITS
     into
    3.36
    Into
    2.83
    into
    2.82
     Into
    2.73
     इनटू
    2.38
     INTO
    2.26
     vào
    2.22
    分成
    1.72
     divided
    1.63
     divides
    1.60
    Activations Density 0.532%

    No Known Activations