© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24880
    Prev
    Next
    INDEX
    Explanations

    some loved ada

    np_acts-logits-general · gemini-2.5-flash-lite

    description of physical objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unger
    0.49
    r
    0.46
    country
    0.43
     હશે
    0.42
    anna
    0.42
    writeData
    0.41
    raft
    0.40
    ]
    0.40
    state
    0.40
    arap
    0.39
    POSITIVE LOGITS
     asegurar
    0.55
     tweeter
    0.50
    MODKEY
    0.50
     megjelen
    0.48
    льной
    0.48
    ்ட்
    0.48
     afbeelding
    0.48
     besonder
    0.47
     desec
    0.47
     anderer
    0.46
    Activations Density 0.001%

    No Known Activations