© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2701
    Prev
    Next
    INDEX
    Explanations

    model response following start tag

    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_17_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
     confidence
    1.30
    <bos>
    1.25
     liability
    1.24
     tav
    1.24
    ene
    1.22
     voulu
    1.17
     salario
    1.16
     combined
    1.15
     amorphous
    1.15
    今回
    1.15
    POSITIVE LOGITS
    at
    1.88
    𝙞
    1.85
    Eternal
    1.70
    𝙤
    1.57
     Thieves
    1.49
    atly
    1.47
    Terror
    1.47
    Elder
    1.47
    Cups
    1.47
    𝙚
    1.46
    Activations Density 0.344%

    No Known Activations