© 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-16K
    7. 8049
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_16k_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
    ب
    0.48
    يال
    0.47
    на
    0.46
    و
    0.46
    म
    0.45
    غي
    0.45
    ياء
    0.45
    بہ
    0.44
    銠
    0.44
    現実
    0.44
    POSITIVE LOGITS
     are
    0.44
     linie
    0.43
     grudnia
    0.43
     समावेश
    0.42
     antler
    0.42
     espuma
    0.42
     조직
    0.42
     tata
    0.42
     मटेरियल
    0.41
    iculaire
    0.41
    Activations Density 0.043%

    No Known Activations