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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80944
    Prev
    Next
    INDEX
    Explanations

    graded linear maps

    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
    Belfast
    -0.81
     Belfast
    -0.79
    ယ်
    -0.78
     Lenz
    -0.73
     PRL
    -0.71
     "','
    -0.69
    쟁
    -0.69
    チャン
    -0.69
     Kamin
    -0.69
     cielos
    -0.69
    POSITIVE LOGITS
     linear
    1.63
    linear
    1.45
     Linear
    1.43
    Linear
    1.34
    LINEAR
    1.26
     linearity
    1.26
     homomorphism
    1.10
    线性
    1.00
     LINEAR
    1.00
     derivation
    0.95
    Activations Density 0.045%

    No Known Activations