© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33290
    Prev
    Next
    INDEX
    Explanations

    android or rhyme

    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
     infringe
    0.46
    بتدي
    0.44
     fuse
    0.44
     [/
    0.44
     sop
    0.43
    ポスト
    0.42
     betrokken
    0.42
     až
    0.41
     $.
    0.41
     on
    0.40
    POSITIVE LOGITS
     ciep
    0.50
    স
    0.50
    вим
    0.48
     이유는
    0.48
     چھ
    0.48
    ahirkan
    0.45
    జె
    0.45
     热
    0.44
    𝐦
    0.44
     Nası
    0.44
    Activations Density 0.001%

    No Known Activations