© 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. 48773
    Prev
    Next
    INDEX
    Explanations

    streets connected by and

    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
    Typically
    -1.34
     viera
    -1.20
    Normally
    -1.13
     typically
    -1.09
     Typically
    -1.08
     komment
    -1.01
    ؽ
    -1.00
     Basically
    -0.99
    dö
    -0.98
    Basically
    -0.96
    POSITIVE LOGITS
     between
    1.10
     pomiędzy
    1.06
     sujetos
    1.03
     bleak
    1.02
    PROTOBUF
    1.01
     BETWEEN
    0.98
    monia
    0.98
     Between
    0.94
    pherds
    0.92
    apin
    0.92
    Activations Density 0.004%

    No Known Activations