© 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. 87156
    Prev
    Next
    INDEX
    Explanations

    suicide ideation victims bombers substrate

    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
    re
    -3.23
     sorta
    -3.17
    '
    -2.94
     soo
    -2.78
     :
    -2.52
    ar
    -2.50
     :-
    -2.45
    os
    -2.41
    .:
    -2.41
    ):
    -2.38
    POSITIVE LOGITS
    𓋼
    3.42
    ズニー
    2.89
     که
    2.69
     parachoque
    2.63
    鱧
    2.59
    𖡼
    2.59
    cherichia
    2.52
    เพื่อ
    2.44
     bekämp
    2.44
     voorbeeld
    2.42
    Activations Density 0.005%

    No Known Activations