© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26194
    Prev
    Next
    INDEX
    Explanations

    Doctor Who, Harry Potter, Pop topics

    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
     हूं
    -1.16
     кү
    -1.10
    kedés
    -1.06
     acestei
    -1.03
     there
    -1.02
    他们是
    -1.02
    vaných
    -1.02
    当たり前
    -1.02
     urged
    -1.00
     Rine
    -1.00
    POSITIVE LOGITS
     was
    1.41
    甚至
    1.27
    ICKNESS
    1.18
    ckeye
    1.13
     incluso
    1.11
     onwards
    1.11
     наиболее
    1.10
     beiden
    1.04
    thodoxy
    1.03
    pecies
    1.02
    Activations Density 0.025%

    No Known Activations