© 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. 1330
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives preceding nouns

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

    safe and

    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
     của
    0.52
     itr
    0.43
     '.</
    0.42
     miatt
    0.41
     iccad
    0.39
    }$.
    0.38
     BLUENRG
    0.38
     aident
    0.37
     viya
    0.37
     UNNEEDED
    0.37
    POSITIVE LOGITS
    -
    0.55
    ley
    0.44
    ,
    0.39
    est
    0.36
     and
    0.36
    istically
    0.36
     h
    0.35
     red
    0.35
    h
    0.34
     high
    0.33
    Activations Density 1.070%

    No Known Activations