© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57483
    Prev
    Next
    INDEX
    Explanations

    meeting criteria or requirements

    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_34/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
     asemenea
    -1.06
     trastornos
    -0.95
    égal
    -0.95
     agujero
    -0.93
    Nassau
    -0.93
     complying
    -0.90
    瓤
    -0.90
     zurückge
    -0.89
     hermosos
    -0.88
     görüntüleri
    -0.88
    POSITIVE LOGITS
     by
    1.41
     of
    1.23
     outlined
    1.20
     despite
    1.18
     requirements
    1.16
     while
    1.08
     posed
    1.03
    continence
    1.02
     regarding
    1.01
     designed
    0.97
    Activations Density 0.063%

    No Known Activations