© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71178
    Prev
    Next
    INDEX
    Explanations

    past tense action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    It
    -1.63
    能夠
    -1.59
    9
    -1.56
     gdyby
    -1.50
     Depending
    -1.44
     reager
    -1.43
     mesmas
    -1.43
     it
    -1.41
    訟
    -1.38
     Generally
    -1.35
    POSITIVE LOGITS
    seems
    1.64
     against
    1.57
    honestly
    1.56
     into
    1.42
    idk
    1.40
     to
    1.38
    igree
    1.37
    Ｕ
    1.36
    derdag
    1.36
    zzie
    1.34
    Activations Density 0.039%

    No Known Activations