© 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. 4929
    Prev
    Next
    INDEX
    Explanations

    sol followed by ability, itude, or ubility

    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
    ROOM
    1.00
     отдельно
    0.95
     расходы
    0.90
     bacon
    0.89
    𝗅
    0.88
    cadilly
    0.88
     hadir
    0.87
     scones
    0.87
    UA
    0.87
    보
    0.87
    POSITIVE LOGITS
    ihull
    1.39
    itary
    1.28
    itude
    1.24
    stice
    1.21
    itud
    1.15
     проблемы
    1.08
    ubility
    1.07
    vable
    1.07
     problemas
    1.07
     problems
    1.04
    Activations Density 0.097%

    No Known Activations