© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38224
    Prev
    Next
    INDEX
    Explanations

    programmatic interface keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vương
    -0.91
     Những
    -0.88
     одним
    -0.88
     --
    -0.85
     désolés
    -0.85
     heiligen
    -0.85
     hervorragend
    -0.84
     freut
    -0.84
     beliebt
    -0.84
     일반
    -0.83
    POSITIVE LOGITS
    pady
    1.26
    providedIn
    1.18
    isée
    1.18
     byen
    1.12
     endforeach
    1.10
     appris
    1.09
    érer
    1.08
    колко
    1.07
     Dette
    1.07
    izzato
    1.07
    Activations Density 0.023%

    No Known Activations