© 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. 116946
    Prev
    Next
    INDEX
    Explanations

    cheap + noun

    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
     cresc
    -1.09
    妧
    -1.09
    mbgg
    -1.04
    ピアノ
    -1.02
     significantly
    -1.02
     simpl
    -1.02
     poft
    -0.98
     amazingly
    -0.96
     epide
    -0.96
     absurd
    -0.95
    POSITIVE LOGITS
     cheap
    1.55
     thrills
    1.55
    skate
    1.49
     Cheap
    1.41
    Cheap
    1.37
    cheap
    1.33
    east
    1.20
     ONLY
    1.19
    sk
    1.17
    ened
    1.14
    Activations Density 0.007%

    No Known Activations