© 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. 231475
    Prev
    Next
    INDEX
    Explanations

    upstairs and downstairs locations

    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
     endExpNow
    0.50
    溟
    0.42
     możemy
    0.41
    JY
    0.41
     riesce
    0.40
     deniz
    0.40
    ZE
    0.40
    ziest
    0.40
     sceGu
    0.40
    UEN
    0.39
    POSITIVE LOGITS
     stairs
    0.63
     staircase
    0.62
     stairway
    0.58
    ա
    0.53
    stairs
    0.53
     payable
    0.53
     hallway
    0.52
     basement
    0.50
     stair
    0.50
    吗
    0.48
    Activations Density 0.005%

    No Known Activations