© 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. 196120
    Prev
    Next
    INDEX
    Explanations

    state facts

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

    no room for ambiguity

    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
     cursed
    0.44
    ようだ
    0.43
     evidently
    0.43
    으나
    0.42
    地
    0.42
     disruptive
    0.41
     discredited
    0.41
                    
    0.40
    今
    0.40
    那边
    0.40
    POSITIVE LOGITS
     ]),
    0.50
    ADT
    0.46
    ADH
    0.46
    randrange
    0.46
    purch
    0.44
     ይቀ
    0.44
    arange
    0.43
    ULTURE
    0.43
     Stimmung
    0.43
    adt
    0.43
    Activations Density 0.004%

    No Known Activations