© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128163
    Prev
    Next
    INDEX
    Explanations

    specific entities and associated terms

    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
     motoru
    -1.45
     triko
    -1.38
    origami
    -1.30
    dolphin
    -1.29
    mga
    -1.28
    nhung
    -1.27
     rése
    -1.24
     Verkäufer
    -1.23
     freundlichen
    -1.22
    roland
    -1.21
    POSITIVE LOGITS
    一种
    1.20
    r
    1.13
    知的
    1.10
    s
    1.10
     as
    1.10
    N
    1.09
     could
    1.09
     unique
    1.06
    u
    1.05
     merito
    1.03
    Activations Density 0.069%

    No Known Activations