© 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. 9720
    Prev
    Next
    INDEX
    Explanations

    with any, some, the, respect, sound

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

    with followed by an article

    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
    ennzeichnet
    0.33
    楎
    0.32
    枺
    0.31
     setzen
    0.31
    ard
    0.30
    ien
    0.30
    imde
    0.30
    }_{+}
    0.30
    werden
    0.29
    knopf
    0.29
    POSITIVE LOGITS
    는
    0.44
     this
    0.40
     a
    0.38
     that
    0.38
    y
    0.37
    は
    0.37
    l
    0.37
    ה
    0.34
     gusto
    0.33
    1
    0.33
    Activations Density 0.462%

    No Known Activations