© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77624
    Prev
    Next
    INDEX
    Explanations

    blocking, obstructing, obscuring

    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
    abandoned
    -0.80
     Anch
    -0.78
     içinde
    -0.72
    Anch
    -0.71
    Isra
    -0.71
    airbnb
    -0.70
    Sentry
    -0.69
    playable
    -0.69
    achsen
    -0.68
     إيران
    -0.68
    POSITIVE LOGITS
     blocked
    3.55
     blocking
    3.20
     obstructed
    3.09
    blocked
    2.95
     obstruction
    2.94
     obsc
    2.88
    Blocking
    2.80
    blocking
    2.77
     obscured
    2.72
    遮
    2.72
    Activations Density 0.098%

    No Known Activations