© 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. 25327
    Prev
    Next
    INDEX
    Explanations

    spatial orientation and axes

    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
    terrasse
    -1.27
    ：……
    -1.20
    fotografie
    -1.20
    titure
    -1.18
     décider
    -1.15
    Câ
    -1.14
     dîner
    -1.13
    ¿½
    -1.11
    CARACTER
    -1.07
     storici
    -1.07
    POSITIVE LOGITS
     bosques
    1.19
    prender
    1.16
    īgā
    1.15
     both
    1.11
    gencias
    1.09
     their
    1.09
     associée
    1.05
    licante
    1.05
    に来
    1.04
     attempting
    1.03
    Activations Density 0.047%

    No Known Activations