© 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. 258113
    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
    棫
    0.51
     berguna
    0.50
     caracteriza
    0.50
    իտ
    0.48
     өл
    0.48
     ministro
    0.47
    लिनी
    0.47
    FICATION
    0.47
     mengembangkan
    0.47
     futuro
    0.46
    POSITIVE LOGITS
    _
    0.52
    ts
    0.50
     Hanford
    0.46
    ject
    0.44
    amp
    0.43
    lass
    0.43
    us
    0.43
    TS
    0.43
    gs
    0.43
    and
    0.42
    Activations Density 0.000%

    No Known Activations