© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21165
    Prev
    Next
    INDEX
    Explanations

    staircases and stairwells

    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_40_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
    ----------
    0.42
    細
    0.41
    esper
    0.40
     epit
    0.38
     sentence
    0.38
    Relations
    0.37
    sentence
    0.37
    Van
    0.36
    一行
    0.36
    呔
    0.36
    POSITIVE LOGITS
     stair
    0.55
     landings
    0.51
     Stair
    0.49
     enclosures
    0.46
     enclosed
    0.44
     enclosure
    0.44
     towers
    0.42
     лест
    0.41
     Spiral
    0.41
     Exit
    0.40
    Activations Density 0.002%

    No Known Activations