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. 7350
    Prev
    Next
    INDEX
    Explanations

    I'd plus opinion/recommendation

    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
    ted
    1.03
     might
    0.91
     be
    0.89
    దీ
    0.86
     see
    0.85
    seeing
    0.79
    be
    0.77
    d
    0.76
     should
    0.75
     suffice
    0.74
    POSITIVE LOGITS
    ogran
    0.85
     scegli
    0.85
     lancéolées
    0.81
     offrent
    0.81
    írus
    0.79
     провели
    0.78
     echt
    0.78
    မျိုး
    0.77
    ))],
    0.77
    currentSprite
    0.76
    Activations Density 0.032%

    No Known Activations