© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128405
    Prev
    Next
    INDEX
    Explanations

    disruptive, overcoming, remote, function, through

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </sup>
    0.52
    Meter
    0.47
    meters
    0.46
    Sos
    0.46
    кте
    0.45
     институт
    0.45
    )}
    0.44
    ul
    0.44
    дак
    0.43
    }
    0.43
    POSITIVE LOGITS
     reprieve
    0.55
     snow
    0.52
     ಅದನ್ನು
    0.51
     sleigh
    0.49
     snowfall
    0.47
     snowman
    0.47
     bracing
    0.47
     setback
    0.46
     VStack
    0.45
     tractor
    0.45
    Activations Density 0.003%

    No Known Activations