© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34489
    Prev
    Next
    INDEX
    Explanations

    code comments and commands

    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
    ுள்ள
    0.39
     !=
    0.38
    日前
    0.37
    SNL
    0.36
    acjach
    0.36
    这一切
    0.35
     purview
    0.35
     <<
    0.34
    Mar
    0.34
    ("&
    0.33
    POSITIVE LOGITS
     サイド
    0.51
     lado
    0.44
     side
    0.44
     стороны
    0.43
    CreateCharacter
    0.43
     Keci
    0.43
     сторона
    0.43
     стороне
    0.43
     bituminous
    0.42
     muscles
    0.42
    Activations Density 0.000%

    No Known Activations