© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    block size, rewards, imports

    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
    Opinión
    -0.84
    ఘ
    -0.78
     Substituting
    -0.69
    entrySet
    -0.67
     بیان
    -0.66
     Acharya
    -0.66
    acq
    -0.66
    AntiForgeryToken
    -0.65
     batt
    -0.65
    фикации
    -0.65
    POSITIVE LOGITS
     reward
    1.74
     rewards
    1.61
    reward
    1.49
    Reward
    1.45
     Reward
    1.43
    rewards
    1.30
     block
    1.27
     blocks
    1.14
     miners
    1.08
    block
    1.05
    Activations Density 0.008%

    No Known Activations