© 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-65K
    7. 30825
    Prev
    Next
    INDEX
    Explanations

    plain text

    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_65k_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
    c
    0.71
    ”),
    0.66
     Neces
    0.58
     };
    0.55
     APPRO
    0.55
     Looking
    0.55
     amaç
    0.53
     Describe
    0.52
    v
    0.52
     }}=
    0.52
    POSITIVE LOGITS
    对待
    0.49
     المط
    0.49
    ْد
    0.48
    ต่อเนื่อง
    0.48
    مام
    0.47
    اعد
    0.47
    ifers
    0.47
    acements
    0.46
    ♍
    0.46
    дания
    0.46
    Activations Density 0.007%

    No Known Activations