© 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. 34-GEMMASCOPE-RES-131K
    7. 93727
    Prev
    Next
    INDEX
    Explanations

    measurable variables and outcomes

    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
    i
    -1.14
    M
    -1.13
    b
    -1.11
    t
    -1.07
    u
    -1.01
    h
    -1.00
    N
    -0.99
    en
    -0.96
    p
    -0.96
    No
    -0.96
    POSITIVE LOGITS
     that
    1.65
     которые
    1.48
     које
    1.34
     and
    1.26
     вроде
    1.15
    loggen
    1.15
    互联网档案馆
    1.14
     cuentos
    1.11
    lsz
    1.09
    EEN
    1.08
    Activations Density 0.333%

    No Known Activations