© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 254382
    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
     проми
    0.47
    ята
    0.46
     група
    0.42
     мили
    0.41
     యా
    0.40
    ಪ
    0.40
     или
    0.40
    표
    0.40
    бут
    0.39
    Amérique
    0.39
    POSITIVE LOGITS
     Spearman
    0.48
     handles
    0.48
     correlations
    0.48
     Scho
    0.46
     realms
    0.45
    ifiées
    0.45
    ‚
    0.44
     Archers
    0.44
    োপুরি
    0.43
     haunts
    0.43
    Activations Density 0.000%

    No Known Activations