© 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. 49004
    Prev
    Next
    INDEX
    Explanations

    movement and progression

    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
     psicologia
    -0.96
     adatt
    -0.88
    """"
    -0.86
     comprende
    -0.84
     piac
    -0.83
     Theile
    -0.83
     cellulare
    -0.82
    ेंद
    -0.82
     tä
    -0.82
    ########
    -0.82
    POSITIVE LOGITS
     for
    1.12
     through
    1.00
     and
    0.82
     some
    0.80
    īgi
    0.79
    ahalli
    0.78
     on
    0.74
     mould
    0.74
    rasti
    0.74
    ynthetic
    0.73
    Activations Density 0.013%

    No Known Activations