© 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. 33532
    Prev
    Next
    INDEX
    Explanations

    cpu, Ti, carrier, IG, 220, 230, 5, 6

    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
    様な
    -1.70
    ようです
    -1.45
    方がいい
    -1.41
     darunter
    -1.36
    こともあり
    -1.34
     the
    -1.33
    ところに
    -1.32
     such
    -1.30
     sebuah
    -1.30
    ほうがいい
    -1.30
    POSITIVE LOGITS
    を
    1.57
    や
    1.45
    anın
    1.39
    vább
    1.34
    jelasan
    1.34
    礎
    1.33
     или
    1.33
    も
    1.28
     on
    1.27
    <bos>
    1.23
    Activations Density 0.066%

    No Known Activations