© 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. 10-GEMMASCOPE-RES-131K
    7. 128542
    Prev
    Next
    INDEX
    Explanations

    our followed by something

    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_10/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
     Sebuah
    -1.76
    衎
    -1.74
     Some
    -1.69
    følge
    -1.68
     There
    -1.67
    camis
    -1.65
    咴
    -1.63
     Because
    -1.61
    entukan
    -1.61
     mismas
    -1.60
    POSITIVE LOGITS
    h
    2.59
    k
    2.47
    self
    2.45
    al
    2.33
    ri
    2.31
    m
    2.25
    c
    2.19
    r
    2.19
    ra
    2.16
    to
    2.14
    Activations Density 0.051%

    No Known Activations