© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77515
    Prev
    Next
    INDEX
    Explanations

    beam mechanics

    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
    Affiliate
    -0.80
    Erg
    -0.76
     Quark
    -0.71
    Maks
    -0.69
    }`,
    -0.69
     художник
    -0.68
     Blessed
    -0.68
     dictum
    -0.67
    Elek
    -0.67
    więks
    -0.67
    POSITIVE LOGITS
     beam
    1.69
     beams
    1.51
     clamped
    1.30
    beam
    1.29
     Beam
    1.23
     Beams
    1.16
     cantilever
    1.15
    BEAM
    1.11
    Beam
    1.11
     elastic
    1.06
    Activations Density 0.045%

    No Known Activations