© 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. 7581
    Prev
    Next
    INDEX
    Explanations

    date placeholder

    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
    ("/",
    0.74
     deterministic
    0.68
     injection
    0.68
     SPF
    0.67
     mana
    0.67
     babel
    0.67
     hipótesis
    0.66
     hairstyle
    0.66
     spray
    0.66
     gastroenter
    0.65
    POSITIVE LOGITS
    ாள்
    0.74
    फल
    0.69
    망
    0.69
    Regardless
    0.68
    returnData
    0.68
     abhiv
    0.68
    ્યુ
    0.66
    Forg
    0.65
    ស្
    0.64
    Unlike
    0.64
    Activations Density 0.007%

    No Known Activations