© 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. 47826
    Prev
    Next
    INDEX
    Explanations

    header file path

    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
    ebx
    -0.68
     boost
    -0.67
     povr
    -0.66
    SignIn
    -0.64
    EP
    -0.64
     incapable
    -0.64
     spawn
    -0.63
     nod
    -0.63
     mesto
    -0.62
    bilis
    -0.61
    POSITIVE LOGITS
    zyż
    0.72
     spillage
    0.72
     déterminer
    0.71
     USA
    0.70
     movimentos
    0.69
    开关
    0.68
     pazi
    0.67
    circuit
    0.67
     statutes
    0.67
     wewnętr
    0.66
    Activations Density 0.065%

    No Known Activations