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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9568
    Prev
    Next
    INDEX
    Explanations

    tongue

    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
    ท์
    2.83
    й
    2.60
    ды
    2.53
    ство
    2.49
    fica
    2.37
    í
    2.30
    Ο
    2.28
    ૃહ
    2.27
    ोध्या
    2.25
    THREADS
    2.24
    POSITIVE LOGITS
    '_
    2.81
    ej
    2.71
    zelfde
    2.70
    ripción
    2.40
    ein
    2.33
    انک
    2.32
    鳎
    2.29
     sessionId
    2.24
    য়াল
    2.23
     addTo
    2.22
    Activations Density 0.026%

    No Known Activations