© 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. 257462
    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
     explosive
    0.42
    ᅱ
    0.41
    ικ
    0.40
     Ik
    0.40
     Lokal
    0.40
    ্যাল
    0.40
     Chiropractic
    0.39
     tumbuh
    0.39
     Cat
    0.39
    爆发
    0.39
    POSITIVE LOGITS
    },(
    0.49
    aptop
    0.48
    тельным
    0.47
    onent
    0.47
    ри
    0.47
    }+
    0.47
    ）・
    0.46
    వో
    0.46
    tea
    0.46
     modalità
    0.46
    Activations Density 0.000%

    No Known Activations