© 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. 2521
    Prev
    Next
    INDEX
    Explanations

    public and its common collocations

    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
    빵
    0.90
    یں
    0.89
    𝙋
    0.88
    Physics
    0.87
    eg
    0.86
    Ancient
    0.85
    Textures
    0.85
    Experienced
    0.85
    𝑮
    0.84
    Habitat
    0.83
    POSITIVE LOGITS
    廨
    1.38
    ally
    1.35
     outcry
    1.33
     sector
    1.33
    sector
    1.24
     opinion
    1.22
     Sector
    1.21
     purse
    1.17
     Enemy
    1.15
    ación
    1.12
    Activations Density 0.036%

    No Known Activations