© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7395
    Prev
    Next
    INDEX
    Explanations

    some/a few

    np_acts-logits-general · gemini-2.5-flash-lite

    quantity, "some" in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    invariant
    0.48
     pathogenesis
    0.46
    "),
    0.46
     (=
    0.45
     (!
    0.45
     heterogeneous
    0.45
     derives
    0.45
    🤍
    0.45
     fulfils
    0.44
     Universität
    0.44
    POSITIVE LOGITS
     కొన్ని
    0.54
     சிலர்
    0.54
     einige
    0.53
     nějak
    0.53
     alguns
    0.52
     algunas
    0.51
     કેટલાક
    0.50
     Tripp
    0.50
     hauling
    0.49
     některé
    0.49
    Activations Density 0.024%

    No Known Activations