© 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. 31-GEMMASCOPE-2-RES-262K
    7. 23439
    Prev
    Next
    INDEX
    Explanations

    Attraction

    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_31_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
     financials
    0.52
     tastefully
    0.49
     ventas
    0.47
    ┴
    0.47
     Thay
    0.47
     siyah
    0.46
     firef
    0.46
     showcasing
    0.44
    হ
    0.44
     stronghold
    0.43
    POSITIVE LOGITS
    epers
    0.45
     საქართველოს
    0.44
    ায়ের
    0.42
     bioge
    0.41
    agge
    0.40
     विषया
    0.40
    ართველოს
    0.40
    ag
    0.39
    alea
    0.39
    marco
    0.38
    Activations Density 0.008%

    No Known Activations