© 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. 81736
    Prev
    Next
    INDEX
    Explanations

    washed with

    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
     elections
    0.49
     harbour
    0.47
     ambiance
    0.47
     may
    0.46
     myös
    0.46
     mood
    0.46
    /
    0.46
     d
    0.45
     mah
    0.44
     possono
    0.44
    POSITIVE LOGITS
    IFORNIA
    0.44
     большо
    0.43
    ıkları
    0.42
    推广
    0.42
    颠
    0.42
    InEx
    0.42
    ፕሮ
    0.41
     инфра
    0.41
    YSIS
    0.40
    VELOP
    0.39
    Activations Density 0.003%

    No Known Activations