© 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. 7075
    Prev
    Next
    INDEX
    Explanations

    amplifies, aligned with

    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
     சேவை
    0.80
     accueillir
    0.78
     recognise
    0.77
    emploi
    0.74
     recognising
    0.73
     accueille
    0.72
     explorar
    0.71
    ቐ
    0.69
     ofrecer
    0.69
     unrivalled
    0.69
    POSITIVE LOGITS
     gotten
    0.86
     get
    0.82
    get
    0.71
     sneaky
    0.67
     even
    0.65
     gets
    0.65
    ตัวเอง
    0.65
     getting
    0.64
     Get
    0.64
     got
    0.62
    Activations Density 0.000%

    No Known Activations