© 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. 12523
    Prev
    Next
    INDEX
    Explanations

    phone bill

    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
    lichess
    0.46
    skich
    0.45
    pcm
    0.44
     இலவச
    0.43
    ření
    0.43
    }=-\
    0.43
    無料
    0.42
    ال
    0.42
    phen
    0.42
    פים
    0.41
    POSITIVE LOGITS
     volatile
    0.43
     단순히
    0.42
     mer
    0.42
     filtro
    0.41
     monitored
    0.41
     August
    0.40
     filter
    0.40
     augmented
    0.39
     semif
    0.39
     haircut
    0.39
    Activations Density 0.012%

    No Known Activations