© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    ready when you are

    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_9_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
    𝓈
    2.46
    𝐻
    2.43
    mages
    2.37
    ко
    2.35
    на
    2.34
    𝑎
    2.32
    ѕ
    2.23
    u
    2.20
     |--
    2.20
    𝑝
    2.18
    POSITIVE LOGITS
    ى
    2.28
     arrivé
    2.26
     jiwa
    2.12
     eröff
    2.12
     voluto
    2.10
     kolej
    2.10
     menghadapi
    2.10
     dute
    2.09
     unchallenged
    2.06
     touchdown
    2.04
    Activations Density 0.086%

    No Known Activations