© 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. 78171
    Prev
    Next
    INDEX
    Explanations

    java imports

    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
     from
    -1.20
     without
    -1.02
     before
    -0.84
     Either
    -0.80
    どちらも
    -0.80
     Aussch
    -0.77
    גי
    -0.77
    elo
    -0.76
     estos
    -0.76
     These
    -0.75
    POSITIVE LOGITS
     java
    1.63
     this
    0.99
    java
    0.94
    ΙΚ
    0.85
    NASDAQ
    0.85
    为例
    0.83
     Moreau
    0.82
    ⑶
    0.82
     javax
    0.81
     adhesivo
    0.81
    Activations Density 0.007%

    No Known Activations