© 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. 256610
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    їз
    0.44
    祟
    0.44
     çox
    0.43
     사라
    0.43
     ನೋ
    0.42
    점에서
    0.42
    γν
    0.42
    假的
    0.42
     സ്ത്ര
    0.41
     korban
    0.41
    POSITIVE LOGITS
    લ્ડ
    0.46
    uet
    0.44
     органами
    0.43
     ог
    0.43
     предложения
    0.42
    𝙞
    0.42
     interventions
    0.42
    ent
    0.41
    ાલુ
    0.41
    meng
    0.41
    Activations Density 0.000%

    No Known Activations