© 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. 117731
    Prev
    Next
    INDEX
    Explanations

    stopping hitting absorbing

    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
    tables
    -0.71
     пользу
    -0.69
     réfrigérateur
    -0.69
    ക്ക്
    -0.69
     risult
    -0.69
    储
    -0.68
    RANDOM
    -0.68
    以為
    -0.68
    сиона
    -0.68
    트
    -0.67
    POSITIVE LOGITS
     hitting
    1.23
     stopping
    1.23
     absorbing
    1.20
     Absorption
    1.16
     absorption
    1.16
     Absor
    1.13
     absorbed
    1.08
    hitting
    1.05
     exit
    1.05
    Absor
    1.03
    Activations Density 0.042%

    No Known Activations