Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7344
    Prev
    Next
    INDEX
    Explanations

    identifiers and numbers

    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_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
    ఞ
    0.76
    Imidazole
    0.75
    Contato
    0.74
    Ᏹ
    0.74
    Nuevo
    0.74
    Gray
    0.72
    Benzyloxy
    0.71
    Condensed
    0.70
    Expansion
    0.70
    ױ
    0.70
    POSITIVE LOGITS
     not
    0.81
     break
    0.78
     self
    0.78
    :
    0.75
     distinctive
    0.72
     family
    0.72
     fine
    0.71
     one
    0.71
     damage
    0.70
     frustrating
    0.69
    Activations Density 0.040%

    No Known Activations