© 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. 54768
    Prev
    Next
    INDEX
    Explanations

    allows for smaller or larger

    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
     جنب
    0.42
    導致
    0.42
     Much
    0.40
     legit
    0.40
     служба
    0.40
     cumple
    0.39
    휋
    0.39
    carbam
    0.38
    Multiple
    0.38
    影響
    0.38
    POSITIVE LOGITS
    際の
    0.48
    воре
    0.47
     terrified
    0.46
     macrom
    0.46
     nanoc
    0.45
     XIA
    0.45
     CASH
    0.43
    ຄ
    0.43
    🤟
    0.43
    📪
    0.43
    Activations Density 0.003%

    No Known Activations