© 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. 18897
    Prev
    Next
    INDEX
    Explanations

    purpose or intended recipient

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

    intend to or for, meant to or for

    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
     která
    0.55
    c
    0.53
     which
    0.50
    к
    0.50
    ak
    0.50
     c
    0.49
     erstmals
    0.49
    ț
    0.48
     ceny
    0.47
     dementia
    0.47
    POSITIVE LOGITS
     intended
    0.92
    intended
    0.86
     bedo
    0.79
     intend
    0.79
     meant
    0.75
     предназна
    0.70
     destinados
    0.70
     intención
    0.69
     intending
    0.68
     intent
    0.68
    Activations Density 0.050%

    No Known Activations