© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110428
    Prev
    Next
    INDEX
    Explanations

    air intake and suction

    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
    veröffentlichung
    -0.81
    蠔
    -0.81
    ilige
    -0.77
     iframe
    -0.77
     emitted
    -0.74
     vej
    -0.73
    发射
    -0.72
     escapes
    -0.71
     disseminated
    -0.71
     escape
    -0.70
    POSITIVE LOGITS
     intake
    2.94
     sucked
    2.50
     sucking
    2.42
     intakes
    2.31
     Intake
    2.28
    intake
    2.14
     sucks
    2.08
     suck
    2.06
     suction
    2.02
    Intake
    1.99
    Activations Density 0.062%

    No Known Activations