© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93960
    Prev
    Next
    INDEX
    Explanations

    podcast episodes and listeners

    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
     editors
    -0.96
    Personen
    -0.84
     Barrera
    -0.82
     fileList
    -0.82
    ffar
    -0.81
     onBackPressed
    -0.81
     ilg
    -0.81
     kalian
    -0.80
    municipi
    -0.79
    bahnhof
    -0.79
    POSITIVE LOGITS
     episode
    1.34
     listeners
    1.12
    episode
    1.10
     listener
    1.05
     episodes
    1.05
     Episode
    1.02
    Listener
    0.98
     metody
    0.94
     imple
    0.93
     Episodes
    0.90
    Activations Density 0.014%

    No Known Activations