© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89471
    Prev
    Next
    INDEX
    Explanations

    image, alt text, title tags

    np_acts-logits-general · gemini-2.5-flash-lite

    image descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    labels
    0.46
     Labels
    0.45
    Labels
    0.44
    itsi
    0.43
    ﻔ
    0.42
     labels
    0.41
    ur
    0.41
    olas
    0.41
     labelling
    0.40
     سوری
    0.40
    POSITIVE LOGITS
    একটি
    0.55
     ਇੱਕ
    0.48
    زء
    0.48
    ⿷
    0.46
    дено
    0.46
    }|^{
    0.46
     omfatt
    0.46
     ένα
    0.46
    的一個
    0.46
     počet
    0.46
    Activations Density 0.000%

    No Known Activations