© 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. 131554
    Prev
    Next
    INDEX
    Explanations

    measuring parcels, names, numbers, wine, deals, teaching, advice

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

    technical or structured data descriptions

    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
     I
    0.44
     httpRequest
    0.44
     closet
    0.42
     Igu
    0.42
     bungalows
    0.42
     সূর্য
    0.41
     refurb
    0.41
     Andorra
    0.41
     güneş
    0.40
     pię
    0.40
    POSITIVE LOGITS
    quel
    0.45
    ڇ
    0.43
    durch
    0.43
    اں
    0.43
    йдет
    0.42
     січня
    0.42
    chnitt
    0.41
     सैलरी
    0.40
    idd
    0.40
    𒊩
    0.40
    Activations Density 0.001%

    No Known Activations