© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32512
    Prev
    Next
    INDEX
    Explanations

    have + participle or noun

    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
    ティ
    -1.19
     disparos
    -1.17
    varande
    -1.13
    ázaro
    -1.11
    Ն
    -1.09
    綜合報導
    -1.07
    förmig
    -1.06
    UMENT
    -1.06
     tornillos
    -1.04
    りましたが
    -1.02
    POSITIVE LOGITS
     been
    1.90
     to
    1.55
     also
    1.42
     already
    1.39
     lot
    1.33
     got
    1.27
     come
    1.22
     shown
    1.21
     certain
    1.18
     seen
    1.16
    Activations Density 0.169%

    No Known Activations