© 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. 84275
    Prev
    Next
    INDEX
    Explanations

    similarity and comparison

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

    call, faster, funny, hierarchy, short, repeatedly

    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
     purged
    0.47
    ,,
    0.43
    、
    0.43
     mingled
    0.41
    شی
    0.40
    shuffle
    0.40
     partitioned
    0.40
     oppure
    0.39
    ▪
    0.39
    –
    0.39
    POSITIVE LOGITS
     तपास
    0.44
     могли
    0.44
    itekt
    0.44
    }=(\
    0.43
    डली
    0.43
    रासायनिक
    0.42
     Например
    0.42
    pless
    0.41
     सुझाव
    0.41
    ೮
    0.41
    Activations Density 0.000%

    No Known Activations