© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4160
    Prev
    Next
    INDEX
    Explanations

    examples using e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    ρό
    0.75
     ඉ
    0.72
    ிடம்
    0.71
     restar
    0.67
     সীম
    0.66
    ammelt
    0.66
     Playing
    0.66
     مختصر
    0.65
    ł
    0.65
     pemain
    0.64
    POSITIVE LOGITS
     disruption
    0.66
     update
    0.62
     initiative
    0.62
    Implementation
    0.61
     Initiative
    0.61
     Update
    0.60
     revamp
    0.59
    Detection
    0.59
    Homepage
    0.59
    Replacement
    0.58
    Activations Density 0.059%

    No Known Activations