© 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. 149575
    Prev
    Next
    INDEX
    Explanations

    locations and related context

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

    mathematical or logical definitions

    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
     Gorilla
    0.54
    ipal
    0.52
     gorilla
    0.52
    í
    0.51
    ã
    0.49
     Punjabi
    0.48
    ë
    0.47
    を見
    0.47
     cord
    0.46
     ILLUSTR
    0.46
    POSITIVE LOGITS
    tBleStatus
    0.47
    Risk
    0.44
     außer
    0.43
    Bue
    0.43
    ्हान
    0.42
    बली
    0.42
    swe
    0.40
    Born
    0.40
    FAPI
    0.40
    نان
    0.40
    Activations Density 0.001%

    No Known Activations