© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221544
    Prev
    Next
    INDEX
    Explanations

    quantity and state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    🇺
    0.43
    ᵘ
    0.41
    èves
    0.41
    ég
    0.41
     agent
    0.40
    𝑔
    0.39
    ի
    0.39
     mln
    0.38
    🇬
    0.37
     agente
    0.37
    POSITIVE LOGITS
     lingered
    0.40
     Island
    0.39
    配信
    0.38
     Quis
    0.38
     RFC
    0.38
     отста
    0.37
     आँख
    0.36
     Sorrow
    0.36
     Nana
    0.35
     Herr
    0.35
    Activations Density 0.002%

    No Known Activations