© 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. 34-GEMMASCOPE-RES-131K
    7. 70294
    Prev
    Next
    INDEX
    Explanations

    Apple stores

    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_34/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
     used
    -1.30
     first
    -1.26
     what
    -1.26
     in
    -1.22
     well
    -1.20
     most
    -1.18
     particularly
    -1.17
    пью
    -1.15
     because
    -1.15
     more
    -1.06
    POSITIVE LOGITS
    tierte
    1.20
     ekip
    1.15
     EVEN
    1.14
     sekret
    1.14
    ꪻ
    1.13
    뻣
    1.13
     [''],
    1.07
     jednej
    1.06
     tamaños
    1.06
     différente
    1.05
    Activations Density 0.000%

    No Known Activations