© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62958
    Prev
    Next
    INDEX
    Explanations

    exact sequences

    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
     policy
    -0.90
     Policy
    -0.87
    Ճ
    -0.84
    policy
    -0.84
    Policy
    -0.80
     EMPTY
    -0.78
     Oscill
    -0.77
    gru
    -0.76
     gru
    -0.75
    rule
    -0.75
    POSITIVE LOGITS
     sequence
    1.70
     exact
    1.63
    Sequence
    1.48
     Sequence
    1.44
    sequence
    1.41
     short
    1.30
     SEQ
    1.28
     sequences
    1.27
     Exact
    1.26
    SEQUENCE
    1.25
    Activations Density 0.025%

    No Known Activations