© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7616
    Prev
    Next
    INDEX
    Explanations

    structured data, lists, options

    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
    down
    1.06
    utter
    1.02
    ли
    1.01
     mercenary
    1.01
    and
    1.00
     fucking
    1.00
     passionate
    0.99
    ,
    0.97
     fence
    0.96
     reputation
    0.96
    POSITIVE LOGITS
    $-$,
    1.94
    omitempty
    1.55
     valamint
    1.44
    ﺎ
    1.44
    Otros
    1.40
    一个
    1.36
     illetve
    1.34
     bzw
    1.33
    Estos
    1.33
     Ա
    1.31
    Activations Density 0.112%

    No Known Activations