© 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. 57659
    Prev
    Next
    INDEX
    Explanations

    climb up

    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
     bogs
    -0.82
     Touring
    -0.79
     Paging
    -0.78
     باسم
    -0.77
    Entering
    -0.76
    buried
    -0.76
     Turning
    -0.75
    掩
    -0.75
    ellees
    -0.75
    trout
    -0.75
    POSITIVE LOGITS
     climb
    3.19
     climbed
    3.03
     climbing
    2.84
     climbs
    2.73
    climb
    2.41
    Climb
    2.33
     Climb
    2.28
     Climbing
    2.09
    climbing
    2.06
     climber
    2.02
    Activations Density 0.046%

    No Known Activations