© 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. 54812
    Prev
    Next
    INDEX
    Explanations

    way to

    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
    ayam
    0.45
    ailable
    0.45
     кілька
    0.44
     Ні
    0.43
    ırı
    0.41
    ῾
    0.41
    旄
    0.40
    capac
    0.40
    '!
    0.39
    incre
    0.39
    POSITIVE LOGITS
    ፔ
    0.46
     spree
    0.44
     pedra
    0.43
     courtship
    0.43
     stderr
    0.42
     amuse
    0.42
     divide
    0.41
     stair
    0.41
     lich
    0.41
     remar
    0.41
    Activations Density 0.001%

    No Known Activations