© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 62196
    Prev
    Next
    INDEX
    Explanations

    Android App, hemp, year, tip of, after a, viewing angle

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

    still professional or respectful

    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
    ]]);
    0.44
     ADDRESS
    0.41
    ְ
    0.41
    ু
    0.40
    ্বন
    0.38
     الماض
    0.38
    OLYBDENUM
    0.38
    İR
    0.38
    נ
    0.38
    ]<?
    0.37
    POSITIVE LOGITS
     memorabilia
    0.46
    seeds
    0.45
     பொழுது
    0.45
     trink
    0.45
    lines
    0.43
    quelle
    0.42
     आकर्षण
    0.42
     purpure
    0.42
    itare
    0.41
    linien
    0.41
    Activations Density 0.000%

    No Known Activations