© 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. 5921
    Prev
    Next
    INDEX
    Explanations

    types of accommodation

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

    property offers or boasts

    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
    navigationLinks
    0.44
    自分の
    0.43
    ቨ
    0.41
    孖
    0.41
    நிய
    0.40
    𒄩
    0.40
    வி
    0.39
    iotsitewise
    0.39
    jährigen
    0.39
    自分が
    0.39
    POSITIVE LOGITS
     bs
    0.41
     along
    0.40
     suite
    0.39
     anna
    0.38
    ,
    0.38
     ad
    0.38
     c
    0.38
     E
    0.38
     also
    0.38
     ayrıca
    0.38
    Activations Density 0.001%

    No Known Activations