© 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. 22-GEMMASCOPE-RES-131K
    7. 14764
    Prev
    Next
    INDEX
    Explanations

    URL and file paths

    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_22/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
    Sziasztok
    -1.23
     virtudes
    -1.15
     also
    -1.05
     over
    -1.02
     problems
    -1.02
     two
    -1.00
    Suara
    -0.99
     BUT
    -0.99
     voltak
    -0.98
    贄
    -0.96
    POSITIVE LOGITS
    instead
    1.05
    埽
    1.05
    particularly
    1.02
    dont
    1.01
     relais
    0.99
    ulele
    0.96
     –
    0.96
     multicolore
    0.92
     you
    0.92
    embedded
    0.91
    Activations Density 0.014%

    No Known Activations