© 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. 33607
    Prev
    Next
    INDEX
    Explanations

    ISSN references

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

    intractable, unsustainable, stabilization

    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
    गड
    0.43
     हाथी
    0.42
     ശബ്
    0.42
     memória
    0.42
     memoria
    0.41
     foliis
    0.40
    }};
    0.40
     그림
    0.39
     floribus
    0.39
    Stri
    0.39
    POSITIVE LOGITS
    svn
    0.42
     ISSN
    0.37
     inti
    0.37
    <unused62>
    0.36
     initiatives
    0.36
     Bundle
    0.35
     ahli
    0.35
     cleft
    0.35
    downloader
    0.35
     intractable
    0.34
    Activations Density 0.009%

    No Known Activations