© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    time, natural, include, pull, materials, influence

    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
     Make
    0.53
     Her
    0.52
     make
    0.52
     given
    0.52
     Σ
    0.52
     have
    0.51
     Bring
    0.50
     S
    0.50
     HR
    0.49
     Basic
    0.49
    POSITIVE LOGITS
     angrily
    0.78
     disgusting
    0.77
     bloquear
    0.74
     amusing
    0.71
     অশ্লীল
    0.70
    Etiam
    0.68
    NESOTA
    0.68
    DoesNotExist
    0.67
     loudly
    0.67
     sonrisa
    0.66
    Activations Density 0.000%

    No Known Activations