© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75783
    Prev
    Next
    INDEX
    Explanations

    actions sponsored or organized by

    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
    と呼ばれる
    -1.05
    以及
    -1.03
     including
    -0.98
    rsquo
    -0.91
    BY
    -0.90
     mantém
    -0.89
    currPos
    -0.89
     fizeram
    -0.89
     दौरान
    -0.89
    quilo
    -0.87
    POSITIVE LOGITS
     joint
    2.08
    joint
    1.98
     by
    1.83
     jointly
    1.77
     through
    1.42
     совмест
    1.35
     Joint
    1.31
     pursuant
    1.30
     JOINT
    1.27
     cooper
    1.25
    Activations Density 0.084%

    No Known Activations