© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 552
    Prev
    Next
    INDEX
    Explanations

    digits and numerical expressions

    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
     (
    0.35
     $[\
    0.34
     la
    0.34
     ra
    0.33
     religious
    0.33
     soul
    0.31
     enc
    0.31
     me
    0.30
     consciously
    0.30
     impl
    0.30
    POSITIVE LOGITS
     ರಿಂದ
    0.71
    0
    0.65
     млн
    0.63
    9
    0.60
    0
    0.60
    5
    0.58
    8
    0.57
     ಸಾವಿರ
    0.56
    4
    0.56
     уту
    0.56
    Activations Density 3.557%

    No Known Activations