© 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. 25325
    Prev
    Next
    INDEX
    Explanations

    words followed by verbs/objects

    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
    虽
    -1.32
    Ông
    -1.30
    ient
    -1.27
    ৩
    -1.23
    ַּ
    -1.23
    핌
    -1.22
     JTextField
    -1.22
    ִּ
    -1.21
    isieren
    -1.19
     ayant
    -1.18
    POSITIVE LOGITS
     meistens
    1.72
     گیاه
    1.40
     they
    1.27
     남자
    1.27
     because
    1.23
     хорошая
    1.20
     like
    1.20
    近くに
    1.20
    ッキリ
    1.18
    右側
    1.18
    Activations Density 0.010%

    No Known Activations