© 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. 204736
    Prev
    Next
    INDEX
    Explanations

    reasoning & comparison

    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
    ي
    0.59
    ه
    0.51
    )+
    0.48
    zuführen
    0.48
    ).\
    0.47
    POSED
    0.47
    نا
    0.44
    و
    0.44
    e
    0.44
    a
    0.44
    POSITIVE LOGITS
    வனின்
    0.48
     baseApiPath
    0.45
     五
    0.43
    ០
    0.43
     l
    0.42
     elektry
    0.42
     sw
    0.41
     სპეცი
    0.41
    ២
    0.41
     အမျိုး
    0.40
    Activations Density 0.001%

    No Known Activations