© 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. 22-GEMMASCOPE-RES-131K
    7. 73669
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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_22/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
    為に
    -1.13
     menggelar
    -1.12
     erleben
    -1.10
    つづく
    -1.09
     testigo
    -1.04
     verschill
    -1.03
    _
    -0.97
     gewohnt
    -0.96
     distintos
    -0.95
     inderdaad
    -0.95
    POSITIVE LOGITS
    หรือ
    1.16
    ENABLE
    1.13
    Quién
    1.08
     penna
    1.07
    Zubereitung
    1.06
    zystać
    1.05
    vek
    1.01
     interro
    1.00
    đèn
    0.98
    Sabes
    0.97
    Activations Density 0.032%

    No Known Activations