© 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. 98472
    Prev
    Next
    INDEX
    Explanations

    qualifications and units

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

    Core Principle

    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
     እን
    0.53
    ጦ
    0.46
     този
    0.46
     שנים
    0.44
     እንደ
    0.44
     воен
    0.44
     xer
    0.43
    ManyToManyField
    0.42
     መ
    0.42
     zprac
    0.42
    POSITIVE LOGITS
    ).”
    0.48
     RIG
    0.45
    BES
    0.45
    }"
    0.44
    もり
    0.44
    IA
    0.43
    ，
    0.43
    onis
    0.43
    )"
    0.42
     BES
    0.42
    Activations Density 0.000%

    No Known Activations