© 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. 58385
    Prev
    Next
    INDEX
    Explanations

    anticipating or waiting

    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
     fosfor
    -0.82
     навсегда
    -0.81
     Heinemann
    -0.75
    湲
    -0.69
    ❖
    -0.67
    ματος
    -0.67
    momix
    -0.67
    WF
    -0.67
     없습니다
    -0.67
    çados
    -0.66
    POSITIVE LOGITS
     wait
    8.31
     waiting
    6.94
     waited
    6.75
     waits
    6.47
    wait
    6.41
    Wait
    6.13
     Wait
    5.94
     Waiting
    5.28
    waiting
    5.16
    Waiting
    5.13
    Activations Density 0.178%

    No Known Activations